{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OCIJGCU6ZOIZLUOINVLTUQPPCV","short_pith_number":"pith:OCIJGCU6","schema_version":"1.0","canonical_sha256":"7090930a9ecb9195d1c86d573a41ef1541514295d1e1ed18fe696316e7fbedf8","source":{"kind":"arxiv","id":"2604.00784","version":2},"attestation_state":"computed","paper":{"title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Schlaefer, Lennart Maack","submitted_at":"2026-04-01T11:45:28Z","abstract_excerpt":"Surgical video understanding is a crucial prerequisite for advancing Computer-Assisted Surgery. While vision-language models (VLMs) have recently been applied to the surgical domain, existing surgical vision-language datasets lack in capturing and evaluating complex, interleaved spatial-temporal dynamics. Creating large scale datasets that accurately represent fine-grained spatial-temporal relationships in surgical videos is challenging due to costly manual annotations or error-prone generation using large language models. To address this gap, we introduce the SurgSTU-Pipeline, a deterministic"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.00784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T11:45:28Z","cross_cats_sorted":[],"title_canon_sha256":"9c7f3cead1d08802fbaec085806e9472367ba0a6953fd8e1cdeec093d6dd8130","abstract_canon_sha256":"8c9930bbdebb87208f35b87a623e0692782ef4725639d7b29add03374f055334"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:04.715221Z","signature_b64":"BellzGhnF6GAkG2SZ+Uh/0LAoAgaktikQuP7xvF0pBByNGpIIsLTI5OA4v1ORFZeMrAxCkpX0M9X4fS1BGHfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7090930a9ecb9195d1c86d573a41ef1541514295d1e1ed18fe696316e7fbedf8","last_reissued_at":"2026-06-29T01:15:04.714744Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:04.714744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Schlaefer, Lennart Maack","submitted_at":"2026-04-01T11:45:28Z","abstract_excerpt":"Surgical video understanding is a crucial prerequisite for advancing Computer-Assisted Surgery. While vision-language models (VLMs) have recently been applied to the surgical domain, existing surgical vision-language datasets lack in capturing and evaluating complex, interleaved spatial-temporal dynamics. Creating large scale datasets that accurately represent fine-grained spatial-temporal relationships in surgical videos is challenging due to costly manual annotations or error-prone generation using large language models. To address this gap, we introduce the SurgSTU-Pipeline, a deterministic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00784","kind":"arxiv","version":2},"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/2604.00784/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.00784","created_at":"2026-06-29T01:15:04.714803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.00784v2","created_at":"2026-06-29T01:15:04.714803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00784","created_at":"2026-06-29T01:15:04.714803+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCIJGCU6ZOIZ","created_at":"2026-06-29T01:15:04.714803+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCIJGCU6ZOIZLUOI","created_at":"2026-06-29T01:15:04.714803+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCIJGCU6","created_at":"2026-06-29T01:15:04.714803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.08712","citing_title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV","json":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV.json","graph_json":"https://pith.science/api/pith-number/OCIJGCU6ZOIZLUOINVLTUQPPCV/graph.json","events_json":"https://pith.science/api/pith-number/OCIJGCU6ZOIZLUOINVLTUQPPCV/events.json","paper":"https://pith.science/paper/OCIJGCU6"},"agent_actions":{"view_html":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV","download_json":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV.json","view_paper":"https://pith.science/paper/OCIJGCU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.00784&json=true","fetch_graph":"https://pith.science/api/pith-number/OCIJGCU6ZOIZLUOINVLTUQPPCV/graph.json","fetch_events":"https://pith.science/api/pith-number/OCIJGCU6ZOIZLUOINVLTUQPPCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV/action/storage_attestation","attest_author":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV/action/author_attestation","sign_citation":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV/action/citation_signature","submit_replication":"https://pith.science/pith/OCIJGCU6ZOIZLUOINVLTUQPPCV/action/replication_record"}},"created_at":"2026-06-29T01:15:04.714803+00:00","updated_at":"2026-06-29T01:15:04.714803+00:00"}