{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VXHOJU224YO3PEZNKBMUN7DBIM","short_pith_number":"pith:VXHOJU22","canonical_record":{"source":{"id":"2503.13891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T04:34:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b648c053d3d6604fc11d52a5d2f67002e211e4ab03a124e1d4a1f4400d3e914b","abstract_canon_sha256":"d6c223823e07c771e66d9c1965b243729825163f1dde6fda618fd480d7c2312f"},"schema_version":"1.0"},"canonical_sha256":"adcee4d35ae61db7932d505946fc61431050e59c7c9d07beac545f9b82c3af6d","source":{"kind":"arxiv","id":"2503.13891","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13891","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13891v1","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13891","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"VXHOJU224YO3","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_16","alias_value":"VXHOJU224YO3PEZN","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_8","alias_value":"VXHOJU22","created_at":"2026-07-05T10:33:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VXHOJU224YO3PEZNKBMUN7DBIM","target":"record","payload":{"canonical_record":{"source":{"id":"2503.13891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T04:34:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b648c053d3d6604fc11d52a5d2f67002e211e4ab03a124e1d4a1f4400d3e914b","abstract_canon_sha256":"d6c223823e07c771e66d9c1965b243729825163f1dde6fda618fd480d7c2312f"},"schema_version":"1.0"},"canonical_sha256":"adcee4d35ae61db7932d505946fc61431050e59c7c9d07beac545f9b82c3af6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:51.510003Z","signature_b64":"11iwp8RJNUhQHU4CSSlFsL6Yk4B7/r4qv788PGFBprv5A7UgfEYHWIdGPdmDFrLDaFITDf2M1sfdVc+FCyIHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adcee4d35ae61db7932d505946fc61431050e59c7c9d07beac545f9b82c3af6d","last_reissued_at":"2026-07-05T10:33:51.509416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:51.509416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.13891","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3EJfP03dW8g3t18s0cRj9ivupUnEaZkWQ29kU+fDT9frYUMHOOnD0Ni64dlmS8us7PrMJux3/lSCGPdleopAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:27:41.822869Z"},"content_sha256":"bf01acc898560b3d381a4fd9e54fda2a3bf9588fce1acfddf7bdb5c8f51a3d32","schema_version":"1.0","event_id":"sha256:bf01acc898560b3d381a4fd9e54fda2a3bf9588fce1acfddf7bdb5c8f51a3d32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VXHOJU224YO3PEZNKBMUN7DBIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Where do Large Vision-Language Models Look at when Answering Questions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chia-Wen Kuo, Fan Chen, Li Fuxin, Longyin Wen, Ming Li, Sijie Zhu, Xiaoying Xing, Ying Wu, Yulei Niu","submitted_at":"2025-03-18T04:34:43Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do LVLMs rely on visual input, and which image regions contribute to their responses? It is non-trivial to interpret the free-form generation of LVLMs due to their complicated visual architecture (e.g., multiple encoders and multi-resolution) and variable-length outputs. In this paper, we extend existing heatmap visualization methods (e.g., iGOS++) to support "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13891","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.13891/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qmubd2tlGlGMugPmNODtma5U/MD9MBal/HDLN2fVogoOkWzvGZ99JCOKBp1394DG4h8zFsaT4Q3lVRYwzKyVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:27:41.823378Z"},"content_sha256":"3b0ff4a83bb2945f1e5e8885f0e16d506c3c9cba5e2a864f823405bf3492c1d2","schema_version":"1.0","event_id":"sha256:3b0ff4a83bb2945f1e5e8885f0e16d506c3c9cba5e2a864f823405bf3492c1d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXHOJU224YO3PEZNKBMUN7DBIM/bundle.json","state_url":"https://pith.science/pith/VXHOJU224YO3PEZNKBMUN7DBIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXHOJU224YO3PEZNKBMUN7DBIM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T00:27:41Z","links":{"resolver":"https://pith.science/pith/VXHOJU224YO3PEZNKBMUN7DBIM","bundle":"https://pith.science/pith/VXHOJU224YO3PEZNKBMUN7DBIM/bundle.json","state":"https://pith.science/pith/VXHOJU224YO3PEZNKBMUN7DBIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXHOJU224YO3PEZNKBMUN7DBIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VXHOJU224YO3PEZNKBMUN7DBIM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d6c223823e07c771e66d9c1965b243729825163f1dde6fda618fd480d7c2312f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T04:34:43Z","title_canon_sha256":"b648c053d3d6604fc11d52a5d2f67002e211e4ab03a124e1d4a1f4400d3e914b"},"schema_version":"1.0","source":{"id":"2503.13891","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13891","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13891v1","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13891","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"VXHOJU224YO3","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_16","alias_value":"VXHOJU224YO3PEZN","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_8","alias_value":"VXHOJU22","created_at":"2026-07-05T10:33:51Z"}],"graph_snapshots":[{"event_id":"sha256:3b0ff4a83bb2945f1e5e8885f0e16d506c3c9cba5e2a864f823405bf3492c1d2","target":"graph","created_at":"2026-07-05T10:33:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.13891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do LVLMs rely on visual input, and which image regions contribute to their responses? It is non-trivial to interpret the free-form generation of LVLMs due to their complicated visual architecture (e.g., multiple encoders and multi-resolution) and variable-length outputs. In this paper, we extend existing heatmap visualization methods (e.g., iGOS++) to support ","authors_text":"Chia-Wen Kuo, Fan Chen, Li Fuxin, Longyin Wen, Ming Li, Sijie Zhu, Xiaoying Xing, Ying Wu, Yulei Niu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T04:34:43Z","title":"Where do Large Vision-Language Models Look at when Answering Questions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13891","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf01acc898560b3d381a4fd9e54fda2a3bf9588fce1acfddf7bdb5c8f51a3d32","target":"record","created_at":"2026-07-05T10:33:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d6c223823e07c771e66d9c1965b243729825163f1dde6fda618fd480d7c2312f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T04:34:43Z","title_canon_sha256":"b648c053d3d6604fc11d52a5d2f67002e211e4ab03a124e1d4a1f4400d3e914b"},"schema_version":"1.0","source":{"id":"2503.13891","kind":"arxiv","version":1}},"canonical_sha256":"adcee4d35ae61db7932d505946fc61431050e59c7c9d07beac545f9b82c3af6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adcee4d35ae61db7932d505946fc61431050e59c7c9d07beac545f9b82c3af6d","first_computed_at":"2026-07-05T10:33:51.509416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:51.509416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11iwp8RJNUhQHU4CSSlFsL6Yk4B7/r4qv788PGFBprv5A7UgfEYHWIdGPdmDFrLDaFITDf2M1sfdVc+FCyIHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:51.510003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13891","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf01acc898560b3d381a4fd9e54fda2a3bf9588fce1acfddf7bdb5c8f51a3d32","sha256:3b0ff4a83bb2945f1e5e8885f0e16d506c3c9cba5e2a864f823405bf3492c1d2"],"state_sha256":"2a27c6dbc13ade75c4791adf506af584cc8ff66c0870e2b23aeb3454969a4b72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kkGU8G22qnO6OXUW37bYW4izAtWKTtOOOsCc/iAuLEahIwa2wyWOp1TMRC0hdfStHrWDcsdEMuNKupWROPMYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:27:41.828908Z","bundle_sha256":"2acd7a882123cc5840d1ecdaa3f1291056317eafe9a5cd0d13cb1e3f81561b14"}}