along/Mars-RAG-paper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

删掉跨分辨率对齐

Browse Source
This commit is contained in:
龙澳
2026-04-08 10:38:22 +08:00
parent c68f896029
commit 9377fc82cd
5 changed files with 83 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
MarsRAG/MarsRAG.aux
View File

@@ -3,8 +3,6 @@
\citation{Malin07CTX} \citation{Malin07CTX}
\citation{Murchie07CRISM} \citation{Murchie07CRISM}
\citation{Smith01MOLA} \citation{Smith01MOLA}
\citation{Grotzinger12Curiosity}
\citation{Li21ZhuRong}
\citation{Wang26marsretrieval} \citation{Wang26marsretrieval}
\citation{Cai25LLM} \citation{Cai25LLM}
\citation{Lewis20RAG} \citation{Lewis20RAG}
@@ -34,8 +32,8 @@
\newlabel{equ:embedding mapping}{{7}{4}} \newlabel{equ:embedding mapping}{{7}{4}}
\newlabel{equ:Spatial Scale-Curvature Correspondence}{{8}{4}} \newlabel{equ:Spatial Scale-Curvature Correspondence}{{8}{4}}
\newlabel{equ:Cross-Reference-Frame Alignment}{{9}{4}} \newlabel{equ:Cross-Reference-Frame Alignment}{{9}{4}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-C}}Spatiotemporal Retrieval with Cross-Resolution Aggregation}{5}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {III-C}}Spatiotemporal Retrieval with Cross-Resolution Aggregation}{4}{}\protected@file@percent }
\newlabel{sec:retrieval}{{\mbox {III-C}}{5}} \newlabel{sec:retrieval}{{\mbox {III-C}}{4}}
\newlabel{equ:Spatial Intent Extraction and Hyperedge Retrieval}{{10}{5}} \newlabel{equ:Spatial Intent Extraction and Hyperedge Retrieval}{{10}{5}}
\newlabel{equ:spatiotemporal encoding}{{11}{5}} \newlabel{equ:spatiotemporal encoding}{{11}{5}}
\newlabel{equ:hyperbolic spatial encoding}{{12}{5}} \newlabel{equ:hyperbolic spatial encoding}{{12}{5}}
@@ -59,24 +57,25 @@
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-D}}Ablation Study (Q3)}{9}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-D}}Ablation Study (Q3)}{9}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {IV}{\ignorespaces Ablation Experiments of HySH and PICT Modules}}{10}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {IV}{\ignorespaces Ablation Experiments of HySH and PICT Modules}}{10}{}\protected@file@percent }
\newlabel{table_ablation}{{IV}{10}} \newlabel{table_ablation}{{IV}{10}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-E}}Conflict Preservation Evaluation (Q4)}{10}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {V}{\ignorespaces Conflict Handling Performance on MarsConflict-50}}{10}{}\protected@file@percent } \@writefile{lot}{\contentsline {table}{\numberline {V}{\ignorespaces Conflict Handling Performance on MarsConflict-50}}{10}{}\protected@file@percent }
\newlabel{table_conflict}{{V}{10}} \newlabel{table_conflict}{{V}{10}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-E}}Conflict Preservation Evaluation (Q4)}{10}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {VI}{\ignorespaces Time Cost Analysis Across Modules}}{10}{}\protected@file@percent }
\newlabel{table_time_cost}{{VI}{10}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-F}}Efficiency Analysis (Q5)}{10}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-F}}Efficiency Analysis (Q5)}{10}{}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {VI}{\ignorespaces Time Cost Analysis Across Modules}}{11}{}\protected@file@percent }
\newlabel{table_time_cost}{{VI}{11}}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-G}}Case Study}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-G}}Case Study}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-H}}Limitations}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-H}}Limitations}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-I}}Related Work}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {section}{\numberline {V}Related Work}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-J}}Graph-Structured Retrieval Augmented Generation}{11}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {V-A}}Graph-Structured Retrieval Augmented Generation}{11}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-K}}Hyperbolic Representation Learning for Retrieval}{12}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {V-B}}Hyperbolic Representation Learning for Retrieval}{12}{}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-L}}Knowledge Conflict Detection and Resolution in RAG}{12}{}\protected@file@percent } \@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {V-C}}Knowledge Conflict Detection and Resolution in RAG}{12}{}\protected@file@percent }
\bibstyle{IEEEtran} \bibstyle{IEEEtran}
\bibdata{IEEEabrv,references} \bibdata{IEEEabrv,references}
\bibcite{McEwen24HiRISE}{1} \bibcite{McEwen24HiRISE}{1}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {IV-M}}Intelligent Retrieval for Planetary Remote Sensing Data}{13}{}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {V}Conclusion}{13}{}\protected@file@percent }
\bibcite{Malin07CTX}{2} \bibcite{Malin07CTX}{2}
\@writefile{toc}{\contentsline {subsection}{\numberline {\mbox {V-D}}Intelligent Retrieval for Planetary Remote Sensing Data}{13}{}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {VI}Conclusion}{13}{}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{References}{13}{}\protected@file@percent }
\bibcite{Murchie07CRISM}{3} \bibcite{Murchie07CRISM}{3}
\bibcite{Smith01MOLA}{4} \bibcite{Smith01MOLA}{4}
\bibcite{Grotzinger12Curiosity}{5} \bibcite{Grotzinger12Curiosity}{5}
@@ -93,5 +92,4 @@
\bibcite{madhu26hyprag}{16} \bibcite{madhu26hyprag}{16}
\bibcite{liu26truthfulrag}{17} \bibcite{liu26truthfulrag}{17}
\bibcite{tang26diagnosing}{18} \bibcite{tang26diagnosing}{18}
\@writefile{toc}{\contentsline {section}{References}{14}{}\protected@file@percent }
\gdef \@abspage@last{14} \gdef \@abspage@last{14}

138
MarsRAG/MarsRAG.log
View File

@@ -1,4 +1,4 @@
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (MiKTeX 23.4) (preloaded format=pdflatex 2025.10.23) 8 APR 2026 10:00 This is pdfTeX, Version 3.141592653-2.6-1.40.25 (MiKTeX 23.4) (preloaded format=pdflatex 2025.10.23) 8 APR 2026 10:33
entering extended mode entering extended mode
restricted \write18 enabled. restricted \write18 enabled.
%&-line parsing enabled. %&-line parsing enabled.
@@ -412,259 +412,249 @@ Underfull \hbox (badness 2368) in paragraph at lines 63--64
-ing -ing
[] []
[2] [3] [2]
Overfull \hbox (12.1057pt too wide) detected at line 150 Underfull \hbox (badness 2213) in paragraph at lines 98--99
\OT1/ptm/m/n/10 Mars Ex-press, Tianwen-1), the ob-ser-va-tion data $\OML/cmm/m/
it/10 D \OT1/cmr/m/n/10 =
[]
[3]
Overfull \hbox (4.88393pt too wide) detected at line 149
[][] []\OML/cmm/m/it/10 : [][] []\OML/cmm/m/it/10 :
[] []
Underfull \hbox (badness 1910) in paragraph at lines 164--165
[]\OT1/ptm/m/n/10 **Proposition 1** (Spa-tial Scale-Curvature Cor-re-spon-
[]
[4] [4]
Overfull \hbox (9.20645pt too wide) detected at line 204 Overfull \hbox (9.20645pt too wide) detected at line 203
[]\OT1/cmr/bx/n/10 x \OT1/cmr/m/n/10 = [] \OML/cmm/m/it/10 ; []\OT1/cmr/bx/n/10 x \OT1/cmr/m/n/10 = [] \OML/cmm/m/it/10 ;
[] []
Overfull \hbox (2.51953pt too wide) detected at line 209 Overfull \hbox (2.51953pt too wide) detected at line 208
[]\OML/cmm/m/it/10 []\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 e[]; e[]\OT1/cmr/m/n/10 []\OML/cmm/m/it/10 []\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 e[]; e[]\OT1/cmr/m/n/10
) = [] \OML/cmm/m/it/10 ; ) = [] \OML/cmm/m/it/10 ;
[] []
Underfull \hbox (badness 10000) in paragraph at lines 220--221 Underfull \hbox (badness 10000) in paragraph at lines 219--220
[]\OT1/ptm/m/n/10 Given spa-tial ob-ser-va-tion hy-per-edge em-bed-dings []\OT1/ptm/m/n/10 Given spa-tial ob-ser-va-tion hy-per-edge em-bed-dings
[] []
Underfull \hbox (badness 3895) in paragraph at lines 220--221 Underfull \hbox (badness 3895) in paragraph at lines 219--220
\OMS/cmsy/m/n/10 f\OT1/cmr/m/n/10 ^^H(\OML/cmm/m/it/10 f[]\OT1/cmr/m/n/10 )\OMS \OMS/cmsy/m/n/10 f\OT1/cmr/m/n/10 ^^H(\OML/cmm/m/it/10 f[]\OT1/cmr/m/n/10 )\OMS
/cmsy/m/n/10 g[] ^^Z \U/msb/m/n/10 H[]$ \OT1/ptm/m/n/10 with query-relevance we /cmsy/m/n/10 g[] ^^Z \U/msb/m/n/10 H[]$ \OT1/ptm/m/n/10 with query-relevance we
ights $\OML/cmm/m/it/10 w[]$ ights $\OML/cmm/m/it/10 w[]$
[] []
Overfull \hbox (113.53706pt too wide) detected at line 242 Overfull \hbox (113.53706pt too wide) detected at line 241
\OMS/cmsy/m/n/10 H[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 p[]; p[] \OMS/cmsy/m/n/10 \OMS/cmsy/m/n/10 H[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 p[]; p[] \OMS/cmsy/m/n/10
j \OML/cmm/m/it/10 q\OT1/cmr/m/n/10 ) = \OML/cmm/m/it/10 H [] \OMS/cmsy/m/n/10 j \OML/cmm/m/it/10 q\OT1/cmr/m/n/10 ) = \OML/cmm/m/it/10 H [] \OMS/cmsy/m/n/10
^^@ [] [] \OML/cmm/m/it/10 ; ^^@ [] [] \OML/cmm/m/it/10 ;
[] []
[5] [5]
Overfull \hbox (41.67476pt too wide) in paragraph at lines 269--283 Overfull \hbox (41.67476pt too wide) in paragraph at lines 268--282
[][] [][]
[] []
Overfull \hbox (49.71666pt too wide) detected at line 287 Overfull \hbox (49.71666pt too wide) detected at line 286
\OT1/cmr/bx/n/10 z[] \OT1/cmr/m/n/10 = [] \OT1/cmr/bx/n/10 z[] \OT1/cmr/m/n/10 = []
[] []
Underfull \hbox (badness 3019) in paragraph at lines 295--296 Overfull \hbox (10.51593pt too wide) detected at line 298
[]\OT1/ptm/m/n/10 **Proposition 2** (Con-flict Type Sep-a-ra-bil-ity). *The
[]
Overfull \hbox (10.51593pt too wide) detected at line 299
\OML/cmm/m/it/10 C[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 v\OT1/cmr/m/n/10 ) = [] \OML/cmm/m/it/10 C[]\OT1/cmr/m/n/10 (\OML/cmm/m/it/10 v\OT1/cmr/m/n/10 ) = []
[] []
LaTeX Font Info: Trying to load font information for OMS+ptm on input line 3 LaTeX Font Info: Trying to load font information for OMS+ptm on input line 3
22. 21.
(D:\software\ctex\MiKTeX\tex/latex/psnfss\omsptm.fd (D:\software\ctex\MiKTeX\tex/latex/psnfss\omsptm.fd
File: omsptm.fd File: omsptm.fd
) )
LaTeX Font Info: Font shape `OMS/ptm/m/n' in size <10> not available LaTeX Font Info: Font shape `OMS/ptm/m/n' in size <10> not available
(Font) Font shape `OMS/cmsy/m/n' tried instead on input line 322. (Font) Font shape `OMS/cmsy/m/n' tried instead on input line 321.
[6] [6]
Underfull \hbox (badness 10000) in paragraph at lines 376--376 Underfull \hbox (badness 10000) in paragraph at lines 375--375
|[] |[]
[] []
Overfull \hbox (14.39503pt too wide) in paragraph at lines 376--376 Overfull \hbox (14.39503pt too wide) in paragraph at lines 375--375
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 376--376 Underfull \hbox (badness 10000) in paragraph at lines 375--375
|[] |[]
[] []
Overfull \hbox (11.8429pt too wide) in paragraph at lines 376--376 Overfull \hbox (11.8429pt too wide) in paragraph at lines 375--375
[] []
[] []
Overfull \hbox (25.19485pt too wide) in paragraph at lines 379--379 Overfull \hbox (25.19485pt too wide) in paragraph at lines 378--378
[]|[]| []|[]|
[] []
Underfull \hbox (badness 10000) in paragraph at lines 379--379 Underfull \hbox (badness 10000) in paragraph at lines 378--378
|[] |[]
[] []
Overfull \hbox (27.67467pt too wide) in paragraph at lines 379--379 Overfull \hbox (27.67467pt too wide) in paragraph at lines 378--378
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 381--381 Underfull \hbox (badness 10000) in paragraph at lines 380--380
|[] |[]
[] []
Overfull \hbox (18.33882pt too wide) in paragraph at lines 381--381 Overfull \hbox (18.33882pt too wide) in paragraph at lines 380--380
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 383--383 Underfull \hbox (badness 10000) in paragraph at lines 382--382
|[] |[]
[] []
Overfull \hbox (27.23465pt too wide) in paragraph at lines 383--383 Overfull \hbox (27.23465pt too wide) in paragraph at lines 382--382
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 385--385 Underfull \hbox (badness 10000) in paragraph at lines 384--384
|[] |[]
[] []
Overfull \hbox (25.89078pt too wide) in paragraph at lines 385--385 Overfull \hbox (25.89078pt too wide) in paragraph at lines 384--384
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 387--387 Underfull \hbox (badness 10000) in paragraph at lines 386--386
|[] |[]
[] []
Overfull \hbox (14.54706pt too wide) in paragraph at lines 387--387 Overfull \hbox (24.43471pt too wide) in paragraph at lines 386--386
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 389--389 Underfull \hbox (badness 10000) in paragraph at lines 386--386
|[] |[]
[] []
Overfull \hbox (24.43471pt too wide) in paragraph at lines 389--389 Overfull \hbox (30.10707pt too wide) in paragraph at lines 386--386
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 389--389 Underfull \hbox (badness 10000) in paragraph at lines 388--388
|[] |[]
[] []
Overfull \hbox (30.10707pt too wide) in paragraph at lines 389--389 Overfull \hbox (32.7467pt too wide) in paragraph at lines 388--388
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 391--391 Underfull \hbox (badness 10000) in paragraph at lines 388--388
|[] |[]
[] []
Overfull \hbox (32.7467pt too wide) in paragraph at lines 391--391 Overfull \hbox (30.10707pt too wide) in paragraph at lines 388--388
[] []
[] []
Underfull \hbox (badness 10000) in paragraph at lines 391--391 Underfull \hbox (badness 2452) in paragraph at lines 393--394
|[]
[]
Overfull \hbox (30.10707pt too wide) in paragraph at lines 391--391
[]
[]
Underfull \hbox (badness 2452) in paragraph at lines 396--397
[]\OT1/ptm/m/n/10 Additionally, to val-i-date gen-er-al-iza-tion on es-tab-lish []\OT1/ptm/m/n/10 Additionally, to val-i-date gen-er-al-iza-tion on es-tab-lish
ed ed
[] []
[7] [7]
Underfull \hbox (badness 10000) in paragraph at lines 426--427 Underfull \hbox (badness 10000) in paragraph at lines 423--424
[]\OT1/ptm/m/n/10 1) **Stan-dard RAG** [6]: Con-ven-tional retrieval- []\OT1/ptm/m/n/10 1) **Stan-dard RAG** [6]: Con-ven-tional retrieval-
[] []
Underfull \hbox (badness 1603) in paragraph at lines 436--437 Underfull \hbox (badness 1603) in paragraph at lines 433--434
[]\OT1/ptm/m/n/10 5) **Hy-per-GraphRAG** [25]: Hypergraph-based RAG []\OT1/ptm/m/n/10 5) **Hy-per-GraphRAG** [25]: Hypergraph-based RAG
[] []
[8]
Underfull \hbox (badness 2698) in paragraph at lines 490--491 Underfull \hbox (badness 2698) in paragraph at lines 487--488
\OT1/ptm/m/n/10 ti-HopQA), Are-oRAG main-tains com-pet-i-tive per-for-mance \OT1/ptm/m/n/10 ti-HopQA), Are-oRAG main-tains com-pet-i-tive per-for-mance
[] []
[8]
Underfull \hbox (badness 10000) in paragraph at lines 535--535 Underfull \hbox (badness 10000) in paragraph at lines 532--532
[]|\OT1/ptm/m/n/8 w/o In-ter-ac-tion En-tropy (use []|\OT1/ptm/m/n/8 w/o In-ter-ac-tion En-tropy (use
[] []
Underfull \hbox (badness 3271) in paragraph at lines 542--543 Underfull \hbox (badness 3271) in paragraph at lines 539--540
[]\OT1/ptm/m/n/10 **a) HySH Mod-ule Anal-y-sis:** The HySH mod-ule []\OT1/ptm/m/n/10 **a) HySH Mod-ule Anal-y-sis:** The HySH mod-ule
[] []
Underfull \hbox (badness 1917) in paragraph at lines 544--545 Underfull \hbox (badness 1917) in paragraph at lines 541--542
\OT1/ptm/m/n/10 F1 im-prove-ment over Eu-clidean hy-per-graph (49.2% vs. \OT1/ptm/m/n/10 F1 im-prove-ment over Eu-clidean hy-per-graph (49.2% vs.
[] []
[9] [9]
Underfull \hbox (badness 10000) in paragraph at lines 567--567 Underfull \hbox (badness 10000) in paragraph at lines 564--564
[]|\OT1/ptm/m/n/8 Standard []|\OT1/ptm/m/n/8 Standard
[] []
Underfull \hbox (badness 10000) in paragraph at lines 569--569 Underfull \hbox (badness 10000) in paragraph at lines 566--566
[]|\OT1/ptm/m/n/8 MultiRAG []|\OT1/ptm/m/n/8 MultiRAG
[] []
Underfull \hbox (badness 10000) in paragraph at lines 575--575 Underfull \hbox (badness 10000) in paragraph at lines 572--572
[]|\OT1/ptm/b/n/8 AreoRAG []|\OT1/ptm/b/n/8 AreoRAG
[] []
[10] [11] [10]
Underfull \vbox (badness 10000) has occurred while \output is active []
[11]
Package textcomp Info: Symbol \textrightarrow not provided by Package textcomp Info: Symbol \textrightarrow not provided by
(textcomp) font family ptm in TS1 encoding. (textcomp) font family ptm in TS1 encoding.
(textcomp) Default family used instead on input line 667. (textcomp) Default family used instead on input line 664.
Package textcomp Info: Symbol \textrightarrow not provided by Package textcomp Info: Symbol \textrightarrow not provided by
(textcomp) font family ptm in TS1 encoding. (textcomp) font family ptm in TS1 encoding.
(textcomp) Default family used instead on input line 667. (textcomp) Default family used instead on input line 664.
[12{D:/software/ctex/MiKTeX/fonts/enc/dvips/cm-super/cm-super-ts1.enc}] [12{D:/software/ctex/MiKTeX/fonts/enc/dvips/cm-super/cm-super-ts1.enc}]
Underfull \hbox (badness 2495) in paragraph at lines 701--702 Underfull \hbox (badness 2495) in paragraph at lines 698--699
[]\OT1/ptm/m/n/10 This work is sup-ported by the Na-tional Key R&D []\OT1/ptm/m/n/10 This work is sup-ported by the Na-tional Key R&D
[] []
Underfull \hbox (badness 2799) in paragraph at lines 701--702 Underfull \hbox (badness 2799) in paragraph at lines 698--699
\OT1/ptm/m/n/10 Pro-gram of China ``In-ter-gov-ern-men-tal In-ter-na-tional Sci \OT1/ptm/m/n/10 Pro-gram of China ``In-ter-gov-ern-men-tal In-ter-na-tional Sci
- -
[] []
Underfull \hbox (badness 7576) in paragraph at lines 701--702 Underfull \hbox (badness 7576) in paragraph at lines 698--699
\OT1/ptm/m/n/10 ence and Tech-nol-ogy In-no-va-tion Co-op-er-a-tion" (Grant \OT1/ptm/m/n/10 ence and Tech-nol-ogy In-no-va-tion Co-op-er-a-tion" (Grant
[] []
@@ -672,7 +662,7 @@ Underfull \hbox (badness 7576) in paragraph at lines 701--702
Here is how much of TeX's memory you used: Here is how much of TeX's memory you used:
5487 strings out of 476331 5487 strings out of 476331
91455 string characters out of 5797649 91455 string characters out of 5797649
1897660 words of memory out of 5000000 1895660 words of memory out of 5000000
25834 multiletter control sequences out of 15000+600000 25834 multiletter control sequences out of 15000+600000
562405 words of font info for 135 fonts, out of 8000000 for 9000 562405 words of font info for 135 fonts, out of 8000000 for 9000
1145 hyphenation exceptions out of 8191 1145 hyphenation exceptions out of 8191
@@ -699,7 +689,7 @@ r/sfrm1000.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/utmb8a.pfb><D:/so
ftware/ctex/MiKTeX/fonts/type1/urw/times/utmbi8a.pfb><D:/software/ctex/MiKTeX/f ftware/ctex/MiKTeX/fonts/type1/urw/times/utmbi8a.pfb><D:/software/ctex/MiKTeX/f
onts/type1/urw/times/utmr8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/ onts/type1/urw/times/utmr8a.pfb><D:/software/ctex/MiKTeX/fonts/type1/urw/times/
utmri8a.pfb> utmri8a.pfb>
Output written on MarsRAG.pdf (14 pages, 384269 bytes). Output written on MarsRAG.pdf (14 pages, 383557 bytes).
PDF statistics: PDF statistics:
175 PDF objects out of 1000 (max. 8388607) 175 PDF objects out of 1000 (max. 8388607)
0 named destinations out of 1000 (max. 500000) 0 named destinations out of 1000 (max. 500000)

BIN
MarsRAG/MarsRAG.pdf
View File

Binary file not shown.

BIN
MarsRAG/MarsRAG.synctex.gz
View File

Binary file not shown.

24
MarsRAG/MarsRAG.tex
View File

@@ -129,7 +129,6 @@ This section introduces the implementation approach of AreoRAG. As shown in Fig.
The three modules interact through three explicit coupling points: (1) HySH's spatial alignment is a prerequisite for meaningful interaction entropy computation in PICT; (2) the radial depth difference $\Delta r$ from HySH directly feeds into the PICT feature vector as the resolution disparity signal; and (3) PICT's triage results feed back to boost retrieval priority of scientifically interesting regions in subsequent queries. The three modules interact through three explicit coupling points: (1) HySH's spatial alignment is a prerequisite for meaningful interaction entropy computation in PICT; (2) the radial depth difference $\Delta r$ from HySH directly feeds into the PICT feature vector as the resolution disparity signal; and (3) PICT's triage results feed back to boost retrieval priority of scientifically interesting regions in subsequent queries.
\subsection{Hyperbolic Spatial Hypergraph Construction}\label{sec:HySH} \subsection{Hyperbolic Spatial Hypergraph Construction}\label{sec:HySH}
The AreoRAG method begins by constructing a knowledge structure that can faithfully represent the continuous spatiotemporal topology of planetary multi-source data. Unlike MultiRAG's Multi-source Line Graph (MLG), which relies on discrete text entities and binary triples, we introduce a hypergraph structure embedded in hyperbolic space to jointly address edge explosion and spatial scale hierarchy. The AreoRAG method begins by constructing a knowledge structure that can faithfully represent the continuous spatiotemporal topology of planetary multi-source data. Unlike MultiRAG's Multi-source Line Graph (MLG), which relies on discrete text entities and binary triples, we introduce a hypergraph structure embedded in hyperbolic space to jointly address edge explosion and spatial scale hierarchy.
1) Multi-source Spatial Adapter Parsing: We first design a spatial adapter for each observation data source to parse instrument metadata, spatial footprints, temporal windows, and spectral parameters. For orbital remote sensing data (e.g., HiRISE, CTX, CRISM, MOLA), parsing involves extracting the image footprint geometry, ground sampling distance, and spectral band configuration from PDS labels. For derived data products (e.g., DTMs, mineral abundance maps), parsing extracts provenance links to the source observations and processing parameters. All temporal references are unified to Solar Longitude $L_s$ to enable cross-platform temporal comparison. 1) Multi-source Spatial Adapter Parsing: We first design a spatial adapter for each observation data source to parse instrument metadata, spatial footprints, temporal windows, and spectral parameters. For orbital remote sensing data (e.g., HiRISE, CTX, CRISM, MOLA), parsing involves extracting the image footprint geometry, ground sampling distance, and spectral band configuration from PDS labels. For derived data products (e.g., DTMs, mineral abundance maps), parsing extracts provenance links to the source observations and processing parameters. All temporal references are unified to Solar Longitude $L_s$ to enable cross-platform temporal comparison.
@@ -146,7 +145,7 @@ Through the parsed data $D_{Fusion}$, we further extract entities (geological fe
\begin{equation} \begin{equation}
\label{equ:planetary science domain schema} \label{equ:planetary science domain schema}
\sum_{D_i} \left( \{e_1, e_2, \ldots, e_m\} \sqcup \{r_1, r_2, \ldots, r_n\} \sqcup \{f_{spa,1}^n, \ldots, f_{spa,p}^n\} \right). \sum_{D_i}{\left( \{e_1,e_2,...,e_m\}\bigcup{\{r_1,r_2,...,r_n\}}\bigcup{\{f_{spa,1}^{n},...,f_{spa,p}^{n}\}} \right)}.
\end{equation} \end{equation}
2) Spatial Observation Hyperedge Formation: Based on the extracted knowledge base, we construct spatial observation hyperedges that bind co-located multi-source observations into single $n$-ary facts. As formalized in Definition 2, each hyperedge $f_{spa}^n$ encapsulates the instrument, spatial footprint, temporal window, spectral bands, target features, and resolution. In a pairwise binary graph, $k$ co-existing spatial entities require $\binom{k}{2} = O(k^2)$ spatial proximity edges. With hyperedges, a single $n$-ary fact binds all $k$ entities, reducing edge complexity to $O(k)$. This directly resolves the edge explosion problem identified in our analysis of MLG. 2) Spatial Observation Hyperedge Formation: Based on the extracted knowledge base, we construct spatial observation hyperedges that bind co-located multi-source observations into single $n$-ary facts. As formalized in Definition 2, each hyperedge $f_{spa}^n$ encapsulates the instrument, spatial footprint, temporal window, spectral bands, target features, and resolution. In a pairwise binary graph, $k$ co-existing spatial entities require $\binom{k}{2} = O(k^2)$ spatial proximity edges. With hyperedges, a single $n$-ary fact binds all $k$ entities, reducing edge complexity to $O(k)$. This directly resolves the edge explosion problem identified in our analysis of MLG.
@@ -161,28 +160,19 @@ where $g(\ell_{res}) = -\log(\ell_{res} / \ell_{max})$ is a monotone decreasing
This embedding design is motivated by the following observation on the intrinsic geometry of planetary spatial data: This embedding design is motivated by the following observation on the intrinsic geometry of planetary spatial data:
**Proposition 1** (Spatial Scale-Curvature Correspondence). *The planetary spatial observation hierarchy exhibits tree-like branching: each coarser-resolution observation spatially contains multiple finer-resolution observations. Let $N(\ell)$ denote the number of observations at resolution level $\ell$. For remote sensing data with total survey area $A_{coverage}$: Observation~1 (Spatial Scale-Curvature Correspondence). The planetary spatial observation hierarchy exhibits tree-like branching: each coarser-resolution observation spatially contains multiple finer-resolution observations. Let $N(\ell)$ denote the number of observations at resolution level $\ell$. For remote sensing data with total survey area $A_{coverage}$:
\begin{equation} \begin{equation}
\label{equ:Spatial Scale-Curvature Correspondence} \label{equ:Spatial Scale-Curvature Correspondence}
N(\ell) \propto A_{coverage} / \ell^2. N(\ell) \propto A_{coverage} / \ell^2.
\end{equation} \end{equation}
As resolution $\ell$ decreases (finer scale), $N(\ell)$ grows quadratically, exhibiting the exponential branching characteristic of negative-curvature spaces. Therefore, the spatial scale hierarchy is intrinsically hyperbolic, and Euclidean embedding with polynomial volume growth cannot faithfully represent it.* As resolution $\ell$ decreases, $N(\ell)$ grows quadratically, exhibiting the exponential branching characteristic of negative-curvature spaces. Therefore, the spatial scale hierarchy is intrinsically hyperbolic, and Euclidean embedding with polynomial volume growth cannot faithfully represent it.
Through this embedding, global coarse-resolution data (e.g., MOLA topography at ~460 m) is placed near the hyperbolic origin (small radial depth), while local high-resolution data (e.g., HiRISE at 0.3 m) is placed far from the origin (large radial depth). The exponential volume growth of $\mathbb{H}_K^d$ naturally accommodates the exponentially increasing number of observations at finer scales. Through this embedding, global coarse-resolution data (e.g., MOLA topography at ~460 m) is placed near the hyperbolic origin (small radial depth), while local high-resolution data (e.g., HiRISE at 0.3 m) is placed far from the origin (large radial depth). The exponential volume growth of $\mathbb{H}_K^d$ naturally accommodates the exponentially increasing number of observations at finer scales.
4) Cross-Reference-Frame Alignment: Different orbital missions use slightly different coordinate reference frames. We align all observations to a unified global reference via parallel transport on the hyperbolic manifold:
\begin{equation}
\label{equ:Cross-Reference-Frame Alignment}
\Phi_{aligned}(e) = \exp_{o_g}\left(\Gamma_{o_k \to o_g}\left(\log_{o_k}(\Phi_k(e))\right)\right),
\end{equation}
where $\log_{o_k}$ is the logarithmic map at the local reference origin $o_k$, $\Gamma_{o_k \to o_g}$ is the parallel transport operator along the geodesic from $o_k$ to the global origin $o_g$, and $\exp_{o_g}$ is the exponential map at the global origin. Unlike Euclidean affine transformations, hyperbolic parallel transport preserves geodesic distances and radial depth, ensuring that scale hierarchy information is maintained after cross-frame alignment.
Here, we provide a simple example of hyperbolic spatial hypergraph construction. As shown in Fig. 4, an observation region is covered by three orbital sensors at different resolutions: a CTX mosaic (6 m), an HiRISE strip (0.3 m), and a CRISM spectral cube (18 m). In the HySH, the HiRISE observation (finest resolution) is embedded at the largest radial depth, while the CRISM observation (coarsest resolution) is nearest to the origin. A spatial observation hyperedge binds all three observations and their co-located geological features into a single $n$-ary fact, without requiring $O(k^2)$ pairwise edges. Here, we provide a simple example of hyperbolic spatial hypergraph construction. As shown in Fig. 4, an observation region is covered by three orbital sensors at different resolutions: a CTX mosaic (6 m), an HiRISE strip (0.3 m), and a CRISM spectral cube (18 m). In the HySH, the HiRISE observation (finest resolution) is embedded at the largest radial depth, while the CRISM observation (coarsest resolution) is nearest to the origin. A spatial observation hyperedge binds all three observations and their co-located geological features into a single $n$-ary fact, without requiring $O(k^2)$ pairwise edges.
\subsection{Spatiotemporal Retrieval with Cross-Resolution Aggregation}\label{sec:retrieval} \subsection{Spatiotemporal Retrieval with Cross-Resolution Aggregation}\label{sec:retrieval}
After the construction of the hyperbolic spatial hypergraph, the next step is to retrieve query-relevant multi-source spatial evidence. The retrieval process comprises two phases: spatiotemporal evidence extraction and cross-resolution aggregation. After the construction of the hyperbolic spatial hypergraph, the next step is to retrieve query-relevant multi-source spatial evidence. The retrieval process comprises two phases: spatiotemporal evidence extraction and cross-resolution aggregation.
@@ -292,7 +282,7 @@ A lightweight classifier maps the feature vector to conflict type:
$$\hat{c} = \arg\max_{c \in \{noise, inst, scale, temp\}} P_\theta(c \mid \mathbf{z}_{conf})$$ $$\hat{c} = \arg\max_{c \in \{noise, inst, scale, temp\}} P_\theta(c \mid \mathbf{z}_{conf})$$
**Proposition 2** (Conflict Type Separability). *The four conflict types are distinguished by orthogonal physical dimensions: $\|\Omega_i - \Omega_j\|$ separates instrument conflicts; $|\log(\ell_{res}^i / \ell_{res}^j)|$ separates scale conflicts; $\Delta\mathcal{T}$ separates temporal conflicts; $\rho_{auth}$ separates noise conflicts. Since these physical features are independent of and complementary to the hidden state features $\mathbf{h}^{(l^*)}_{conf}$ (which encode semantic inconsistency), the four conflict types are linearly separable in the augmented feature space $\mathbf{z}_{conf}$.* Lemma~1 (Conflict Type Separability). The four conflict types are distinguished by orthogonal physical dimensions: $\|\Omega_i - \Omega_j\|$ separates instrument conflicts; $|\log(\ell_{res}^i / \ell_{res}^j)|$ separates scale conflicts; $\Delta\mathcal{T}$ separates temporal conflicts; $\rho_{auth}$ separates noise conflicts. Since these physical features are independent of and complementary to the hidden state features $\mathbf{h}^{(l^*)}_{conf}$ (which encode semantic inconsistency), the four conflict types are linearly separable in the augmented feature space $\mathbf{z}_{conf}$.
3) Conflict-Aware Confidence Recalibration: Based on the classification result, we recalibrate the node confidence. This is the key departure from MultiRAG's MCC, which uniformly penalizes inconsistency: 3) Conflict-Aware Confidence Recalibration: Based on the classification result, we recalibrate the node confidence. This is the key departure from MultiRAG's MCC, which uniformly penalizes inconsistency:
@@ -579,7 +569,7 @@ A defining capability of AreoRAG is the ability to preserve scientifically valua
Table IV reveals the fundamental difference between AreoRAG and existing methods. MultiRAG achieves a high Noise Rejection Rate (85.7\%) but at the cost of a catastrophically low Conflict Preservation Rate (8.3\%) — it filters 91.7\% of scientifically valuable conflicts as "unreliable data." TruthfulRAG and MetaRAG show similar behavior (CPR of 13.9\% and 11.1\%), confirming that existing conflict-resolution methods systematically destroy scientific anomaly signals. Table IV reveals the fundamental difference between AreoRAG and existing methods. MultiRAG achieves a high Noise Rejection Rate (85.7\%) but at the cost of a catastrophically low Conflict Preservation Rate (8.3\%) — it filters 91.7\% of scientifically valuable conflicts as "unreliable data." TruthfulRAG and MetaRAG show similar behavior (CPR of 13.9\% and 11.1\%), confirming that existing conflict-resolution methods systematically destroy scientific anomaly signals.
In contrast, AreoRAG achieves a CPR of 91.7\% while maintaining the same NRR (85.7\%) as MultiRAG, demonstrating that PICT successfully decouples noise filtering from scientific conflict preservation. The Conflict Classification Accuracy of 84.0\% on the four-category task validates the separability claim in Proposition 2. Error analysis reveals that the primary source of misclassification is between instrument-inherent and scale-dependent conflicts (12.3\% confusion rate), which is expected as both involve observation geometry differences. Noise vs. scientific conflict misclassification is rare (3.7\%), confirming the robustness of the explainable/opaque distinction (Definition 7). In contrast, AreoRAG achieves a CPR of 91.7\% while maintaining the same NRR (85.7\%) as MultiRAG, demonstrating that PICT successfully decouples noise filtering from scientific conflict preservation. The Conflict Classification Accuracy of 84.0\% on the four-category task validates the separability claim in Lemma~1. Error analysis reveals that the primary source of misclassification is between instrument-inherent and scale-dependent conflicts (12.3\% confusion rate), which is expected as both involve observation geometry differences. Noise vs. scientific conflict misclassification is rare (3.7\%), confirming the robustness of the explainable/opaque distinction (Definition 7).
Furthermore, the F1 score improvement (53.1\% vs. 35.2\% for MultiRAG) demonstrates that preserving scientific conflicts directly benefits answer quality: the LLM can generate more comprehensive and scientifically faithful answers when provided with both agreeing and legitimately disagreeing evidence, accompanied by physical bridging explanations. Furthermore, the F1 score improvement (53.1\% vs. 35.2\% for MultiRAG) demonstrates that preserving scientific conflicts directly benefits answer quality: the LLM can generate more comprehensive and scientifically faithful answers when provided with both agreeing and legitimately disagreeing evidence, accompanied by physical bridging explanations.
@@ -643,7 +633,7 @@ We acknowledge several limitations inherent in the current framework:
4) **Generalization to other planetary bodies**: While designed for Mars, the framework's principles (hyperbolic scale hierarchy, physics-informed conflict triage) are applicable to other planetary bodies (Moon, Venus, icy moons). Validation on non-Mars datasets remains future work. 4) **Generalization to other planetary bodies**: While designed for Mars, the framework's principles (hyperbolic scale hierarchy, physics-informed conflict triage) are applicable to other planetary bodies (Moon, Venus, icy moons). Validation on non-Mars datasets remains future work.
\subsection{Related Work} \section{Related Work}
\subsection{Graph-Structured Retrieval Augmented Generation} \subsection{Graph-Structured Retrieval Augmented Generation}
@@ -662,7 +652,7 @@ Hyperbolic geometry has attracted increasing attention in representation learnin
In the context of text retrieval, hyperbolic geometry has recently shown strong promise. HypRAG [20] introduces hyperbolic dense retrieval for RAG, developing two model variants in the Lorentz model: a fully hyperbolic transformer (HyTE-FH) and a hybrid architecture (HyTE-H). A key contribution is the Outward Einstein Midpoint (OEM), a geometry-aware pooling operator that provably preserves hierarchical structure during sequence aggregation, overcoming the radial contraction failure of naive Euclidean averaging. HypRAG achieves up to 29\% gains over Euclidean baselines in context relevance on RAGBench, and demonstrates that hyperbolic representations encode document specificity through norm-based separation — with over 20\% radial increase from general to specific concepts. HyperbolicRAG [58] projects embeddings into the Poincar\'e ball to encode hierarchical depth within a static knowledge graph, using dual-space retrieval that fuses Euclidean and hyperbolic rankings. HELM [59] introduces a family of hyperbolic language models that operate entirely in hyperbolic space for text generation, though not specifically targeting retrieval. In the context of text retrieval, hyperbolic geometry has recently shown strong promise. HypRAG [20] introduces hyperbolic dense retrieval for RAG, developing two model variants in the Lorentz model: a fully hyperbolic transformer (HyTE-FH) and a hybrid architecture (HyTE-H). A key contribution is the Outward Einstein Midpoint (OEM), a geometry-aware pooling operator that provably preserves hierarchical structure during sequence aggregation, overcoming the radial contraction failure of naive Euclidean averaging. HypRAG achieves up to 29\% gains over Euclidean baselines in context relevance on RAGBench, and demonstrates that hyperbolic representations encode document specificity through norm-based separation — with over 20\% radial increase from general to specific concepts. HyperbolicRAG [58] projects embeddings into the Poincar\'e ball to encode hierarchical depth within a static knowledge graph, using dual-space retrieval that fuses Euclidean and hyperbolic rankings. HELM [59] introduces a family of hyperbolic language models that operate entirely in hyperbolic space for text generation, though not specifically targeting retrieval.
These works establish the viability of hyperbolic geometry for hierarchical text retrieval, but they exclusively address the semantic hierarchy of natural language documents (broad topics → specific entities). No existing work has applied hyperbolic geometry to represent the physical scale hierarchy of scientific observations, where the hierarchy arises not from semantic abstraction but from spatial resolution (coarse global survey → fine local imaging). AreoRAG introduces the scale-curvature correspondence principle (Proposition 1), which establishes that the resolution hierarchy of planetary remote sensing data is intrinsically hyperbolic, and couples spatial resolution with radial depth in the Lorentz model. Furthermore, we extend the OEM pooling operator with resolution-aware radial weighting (Spatial OEM, Eq. 13), ensuring that cross-resolution aggregation preserves fine-scale observational details rather than collapsing them into coarse-resolution summaries. These works establish the viability of hyperbolic geometry for hierarchical text retrieval, but they exclusively address the semantic hierarchy of natural language documents (broad topics → specific entities). No existing work has applied hyperbolic geometry to represent the physical scale hierarchy of scientific observations, where the hierarchy arises not from semantic abstraction but from spatial resolution (coarse global survey → fine local imaging). AreoRAG introduces the scale-curvature correspondence principle (Observation 1), which establishes that the resolution hierarchy of planetary remote sensing data is intrinsically hyperbolic, and couples spatial resolution with radial depth in the Lorentz model. Furthermore, we extend the OEM pooling operator with resolution-aware radial weighting (Spatial OEM, Eq. 13), ensuring that cross-resolution aggregation preserves fine-scale observational details rather than collapsing them into coarse-resolution summaries.
\subsection{Knowledge Conflict Detection and Resolution in RAG} \subsection{Knowledge Conflict Detection and Resolution in RAG}