{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY","short_pith_number":"pith:Y7EXQLRS","canonical_record":{"source":{"id":"2411.10937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T02:23:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bdef876cd14da290ed1408af88e789c9dfb8ac828e2f7f45478a47e220c3d51a","abstract_canon_sha256":"e488de28580b92c9484702da291c7eed4ea43878b0c5c43215053214fb1797c7"},"schema_version":"1.0"},"canonical_sha256":"c7c9782e3269eeea8f3f8dbd987b1526311a13dc14c753c10ebfcc4cf193520a","source":{"kind":"arxiv","id":"2411.10937","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10937","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10937v1","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10937","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"pith_short_12","alias_value":"Y7EXQLRSNHXO","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"pith_short_16","alias_value":"Y7EXQLRSNHXOVDZ7","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"pith_short_8","alias_value":"Y7EXQLRS","created_at":"2026-07-05T09:36:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T02:23:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bdef876cd14da290ed1408af88e789c9dfb8ac828e2f7f45478a47e220c3d51a","abstract_canon_sha256":"e488de28580b92c9484702da291c7eed4ea43878b0c5c43215053214fb1797c7"},"schema_version":"1.0"},"canonical_sha256":"c7c9782e3269eeea8f3f8dbd987b1526311a13dc14c753c10ebfcc4cf193520a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:25.441053Z","signature_b64":"hArvTsEXwVEqHMwninCZTti9mZu7meDwVmqD9KpErUEeLmzDRv8YjTOEyhxwL1YXCP4gLG5agSZsoBNdloLXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c9782e3269eeea8f3f8dbd987b1526311a13dc14c753c10ebfcc4cf193520a","last_reissued_at":"2026-07-05T09:36:25.440631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:25.440631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10937","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":"2026-07-05T09:36:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O1YnA7iCPkX4aK+ZruU48Q18blvtwsOifZua+xMKTMnXOWuHlCemAQUY2ZlXnOaPtwetmgWeSmgMCS0bybUdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:59:58.300951Z"},"content_sha256":"d0787cbd3b1856fbb363566ae1341a686db6cde40dbaf3f94a6660ba0f118023","schema_version":"1.0","event_id":"sha256:d0787cbd3b1856fbb363566ae1341a686db6cde40dbaf3f94a6660ba0f118023"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiang Liu, Kaishuai Xu, Wenjie Li, Wenjun Hou, Yan Hu, Yi Cheng","submitted_at":"2024-11-17T02:23:45Z","abstract_excerpt":"Comprehensively understanding surgical scenes in Surgical Visual Question Answering (Surgical VQA) requires reasoning over multiple objects. Previous approaches address this task using cross-modal fusion strategies to enhance reasoning ability. However, these methods often struggle with limited scene understanding and question comprehension, and some rely on external resources (e.g., pre-extracted object features), which can introduce errors and generalize poorly across diverse surgical environments. To address these challenges, we propose SCAN, a simple yet effective memory-augmented framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10937","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/2411.10937/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":"2026-07-05T09:36:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WYa1DXlrlbYDZB7575G6RlB/ByLDzpH1kvJWj8wS/Do2u04vwfuHlFHp6eIIiHTBo6+jFOldS+RLpX2pH6MhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:59:58.301332Z"},"content_sha256":"4e39cec7ea681a1785396f4657d596f61abe913052a1bafe9ffddfc32e0cc963","schema_version":"1.0","event_id":"sha256:4e39cec7ea681a1785396f4657d596f61abe913052a1bafe9ffddfc32e0cc963"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY/bundle.json","state_url":"https://pith.science/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY/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":"2026-07-07T07:59:58Z","links":{"resolver":"https://pith.science/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY","bundle":"https://pith.science/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY/bundle.json","state":"https://pith.science/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y7EXQLRSNHXOVDZ7RW6ZQ6YVEY","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":"e488de28580b92c9484702da291c7eed4ea43878b0c5c43215053214fb1797c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T02:23:45Z","title_canon_sha256":"bdef876cd14da290ed1408af88e789c9dfb8ac828e2f7f45478a47e220c3d51a"},"schema_version":"1.0","source":{"id":"2411.10937","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10937","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10937v1","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10937","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"pith_short_12","alias_value":"Y7EXQLRSNHXO","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"pith_short_16","alias_value":"Y7EXQLRSNHXOVDZ7","created_at":"2026-07-05T09:36:25Z"},{"alias_kind":"pith_short_8","alias_value":"Y7EXQLRS","created_at":"2026-07-05T09:36:25Z"}],"graph_snapshots":[{"event_id":"sha256:4e39cec7ea681a1785396f4657d596f61abe913052a1bafe9ffddfc32e0cc963","target":"graph","created_at":"2026-07-05T09:36:25Z","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/2411.10937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Comprehensively understanding surgical scenes in Surgical Visual Question Answering (Surgical VQA) requires reasoning over multiple objects. Previous approaches address this task using cross-modal fusion strategies to enhance reasoning ability. However, these methods often struggle with limited scene understanding and question comprehension, and some rely on external resources (e.g., pre-extracted object features), which can introduce errors and generalize poorly across diverse surgical environments. To address these challenges, we propose SCAN, a simple yet effective memory-augmented framewor","authors_text":"Jiang Liu, Kaishuai Xu, Wenjie Li, Wenjun Hou, Yan Hu, Yi Cheng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T02:23:45Z","title":"Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10937","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:d0787cbd3b1856fbb363566ae1341a686db6cde40dbaf3f94a6660ba0f118023","target":"record","created_at":"2026-07-05T09:36:25Z","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":"e488de28580b92c9484702da291c7eed4ea43878b0c5c43215053214fb1797c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T02:23:45Z","title_canon_sha256":"bdef876cd14da290ed1408af88e789c9dfb8ac828e2f7f45478a47e220c3d51a"},"schema_version":"1.0","source":{"id":"2411.10937","kind":"arxiv","version":1}},"canonical_sha256":"c7c9782e3269eeea8f3f8dbd987b1526311a13dc14c753c10ebfcc4cf193520a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7c9782e3269eeea8f3f8dbd987b1526311a13dc14c753c10ebfcc4cf193520a","first_computed_at":"2026-07-05T09:36:25.440631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:25.440631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hArvTsEXwVEqHMwninCZTti9mZu7meDwVmqD9KpErUEeLmzDRv8YjTOEyhxwL1YXCP4gLG5agSZsoBNdloLXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:25.441053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10937","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0787cbd3b1856fbb363566ae1341a686db6cde40dbaf3f94a6660ba0f118023","sha256:4e39cec7ea681a1785396f4657d596f61abe913052a1bafe9ffddfc32e0cc963"],"state_sha256":"6e785efdc7261978c6e9a231c254ff7d5c2cdad17a9342197235dd7ec1ee2b5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHzSNTtOZ1DEzXYeez0Zlau4dcqY+zhSmYlBbXaOk3UY8Y/aTc2gFb5w1tbe2Om5dNR4sRBEblw9ETm3jjRKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:59:58.303461Z","bundle_sha256":"530ffa7fa51dcaf398952d86a10df6e7a26207464241fddc6234727b8093a313"}}