{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WVHAAXEGZ2A234FEDEVHW3FPGR","short_pith_number":"pith:WVHAAXEG","canonical_record":{"source":{"id":"2408.07981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T07:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6c5238885a0be948e23f6ce80a916bbed3bb82c929c04cf30c9e5ee9f36a834","abstract_canon_sha256":"1fdb33be028877fd68aa19463810fda1a40cbbc8fda15bf5426eadfcf9d64aec"},"schema_version":"1.0"},"canonical_sha256":"b54e005c86ce81adf0a4192a7b6caf3461c1d0769932918777975be7a08d098e","source":{"kind":"arxiv","id":"2408.07981","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07981","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07981v1","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07981","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"WVHAAXEGZ2A2","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_16","alias_value":"WVHAAXEGZ2A234FE","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_8","alias_value":"WVHAAXEG","created_at":"2026-07-05T08:55:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WVHAAXEGZ2A234FEDEVHW3FPGR","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T07:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6c5238885a0be948e23f6ce80a916bbed3bb82c929c04cf30c9e5ee9f36a834","abstract_canon_sha256":"1fdb33be028877fd68aa19463810fda1a40cbbc8fda15bf5426eadfcf9d64aec"},"schema_version":"1.0"},"canonical_sha256":"b54e005c86ce81adf0a4192a7b6caf3461c1d0769932918777975be7a08d098e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:42.742887Z","signature_b64":"2no0R7/46/1+N0p93fjTaDS5V2JmEGJg5HhQbGGNwV9GwQh9X0ma7ZSQdyKn3DDvn+yH5lb8wMeKjkZJIBSWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b54e005c86ce81adf0a4192a7b6caf3461c1d0769932918777975be7a08d098e","last_reissued_at":"2026-07-05T08:55:42.742480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:42.742480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07981","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":"2026-07-05T08:55:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8Zd10T1y9CE7neTK1ukcz8K65AOtC8Q4Ey3NJ/8MHyJDaSSj28mGSDTiG3BiqzPXZnX/6iNCjc4XkKuFpWyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:22:17.528317Z"},"content_sha256":"cb336eb47a75a1abee1310a62fbd86f234d10cecb2a65342b24f2d3993346e7d","schema_version":"1.0","event_id":"sha256:cb336eb47a75a1abee1310a62fbd86f234d10cecb2a65342b24f2d3993346e7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WVHAAXEGZ2A234FEDEVHW3FPGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Brian R Quaranto, Garrett Skinner, Gene Yang, Jiajie Li, Jinjun Xiong, Peter C W Kim, Steven D Schwaitzberg","submitted_at":"2024-08-15T07:00:20Z","abstract_excerpt":"Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal models for videos still lack the capabilities to understand and engage in conversations about surgical videos. One major contributing factor is the absence of datasets in the surgical field. In this paper, we create a new dataset, Surg-QA, consisting of 102,000 surgical video-instruction pairs, the largest of its kind so far. To build such a dataset, we propose a novel two-stage que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07981","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/2408.07981/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":"2026-07-05T08:55:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m32o/8epUS2PHTLkKU5SMnVxVC5ylHQ9rkxwPIE2mQmEHmfiNHzijmQFpyRB/ZhkPRW59WxPMm8+V3k0rOk1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:22:17.528702Z"},"content_sha256":"dc81323b4418733bd7a7240143dad8fec2ffe832428fffe5702210eaabf0f9e9","schema_version":"1.0","event_id":"sha256:dc81323b4418733bd7a7240143dad8fec2ffe832428fffe5702210eaabf0f9e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WVHAAXEGZ2A234FEDEVHW3FPGR/bundle.json","state_url":"https://pith.science/pith/WVHAAXEGZ2A234FEDEVHW3FPGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WVHAAXEGZ2A234FEDEVHW3FPGR/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":"2026-08-06T06:22:17Z","links":{"resolver":"https://pith.science/pith/WVHAAXEGZ2A234FEDEVHW3FPGR","bundle":"https://pith.science/pith/WVHAAXEGZ2A234FEDEVHW3FPGR/bundle.json","state":"https://pith.science/pith/WVHAAXEGZ2A234FEDEVHW3FPGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WVHAAXEGZ2A234FEDEVHW3FPGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WVHAAXEGZ2A234FEDEVHW3FPGR","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":"1fdb33be028877fd68aa19463810fda1a40cbbc8fda15bf5426eadfcf9d64aec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T07:00:20Z","title_canon_sha256":"c6c5238885a0be948e23f6ce80a916bbed3bb82c929c04cf30c9e5ee9f36a834"},"schema_version":"1.0","source":{"id":"2408.07981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07981","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07981v1","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07981","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"WVHAAXEGZ2A2","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_16","alias_value":"WVHAAXEGZ2A234FE","created_at":"2026-07-05T08:55:42Z"},{"alias_kind":"pith_short_8","alias_value":"WVHAAXEG","created_at":"2026-07-05T08:55:42Z"}],"graph_snapshots":[{"event_id":"sha256:dc81323b4418733bd7a7240143dad8fec2ffe832428fffe5702210eaabf0f9e9","target":"graph","created_at":"2026-07-05T08:55:42Z","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/2408.07981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal models for videos still lack the capabilities to understand and engage in conversations about surgical videos. One major contributing factor is the absence of datasets in the surgical field. In this paper, we create a new dataset, Surg-QA, consisting of 102,000 surgical video-instruction pairs, the largest of its kind so far. To build such a dataset, we propose a novel two-stage que","authors_text":"Brian R Quaranto, Garrett Skinner, Gene Yang, Jiajie Li, Jinjun Xiong, Peter C W Kim, Steven D Schwaitzberg","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T07:00:20Z","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07981","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:cb336eb47a75a1abee1310a62fbd86f234d10cecb2a65342b24f2d3993346e7d","target":"record","created_at":"2026-07-05T08:55:42Z","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":"1fdb33be028877fd68aa19463810fda1a40cbbc8fda15bf5426eadfcf9d64aec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T07:00:20Z","title_canon_sha256":"c6c5238885a0be948e23f6ce80a916bbed3bb82c929c04cf30c9e5ee9f36a834"},"schema_version":"1.0","source":{"id":"2408.07981","kind":"arxiv","version":1}},"canonical_sha256":"b54e005c86ce81adf0a4192a7b6caf3461c1d0769932918777975be7a08d098e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b54e005c86ce81adf0a4192a7b6caf3461c1d0769932918777975be7a08d098e","first_computed_at":"2026-07-05T08:55:42.742480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:42.742480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2no0R7/46/1+N0p93fjTaDS5V2JmEGJg5HhQbGGNwV9GwQh9X0ma7ZSQdyKn3DDvn+yH5lb8wMeKjkZJIBSWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:42.742887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07981","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb336eb47a75a1abee1310a62fbd86f234d10cecb2a65342b24f2d3993346e7d","sha256:dc81323b4418733bd7a7240143dad8fec2ffe832428fffe5702210eaabf0f9e9"],"state_sha256":"5c9ee15f53ec3f4cfc720820546fec0def3b050d26c486175471c7d831902ccb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QIxGqDQHfXy+NEX4MUULIrP4p6TFj1KzZqZF3fFFlZSYtIy6VCpCCbJl+ZdoUOqzVXfBzgESyvIuQnzHbxPBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:22:17.532726Z","bundle_sha256":"32897bd0a2cd360063db8ac62c6561fd4335393639ca4d28bfad251809058cfa"}}