{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OCIJGCU6ZOIZLUOINVLTUQPPCV","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":"8c9930bbdebb87208f35b87a623e0692782ef4725639d7b29add03374f055334","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T11:45:28Z","title_canon_sha256":"9c7f3cead1d08802fbaec085806e9472367ba0a6953fd8e1cdeec093d6dd8130"},"schema_version":"1.0","source":{"id":"2604.00784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00784","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00784v2","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00784","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"OCIJGCU6ZOIZ","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"OCIJGCU6ZOIZLUOI","created_at":"2026-06-29T01:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"OCIJGCU6","created_at":"2026-06-29T01:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:103666ee3e94aa8aabd2e1d419102d6a34576720a5502e6024cf3d367eba1576","target":"graph","created_at":"2026-06-29T01:15:04Z","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/2604.00784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Schlaefer, Lennart Maack","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T11:45:28Z","title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00784","kind":"arxiv","version":2},"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:e1bcfd0c87f0a4f3a0b04aa34e76218cbd44b97547bb37bf4ff611455d54c70f","target":"record","created_at":"2026-06-29T01:15:04Z","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":"8c9930bbdebb87208f35b87a623e0692782ef4725639d7b29add03374f055334","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T11:45:28Z","title_canon_sha256":"9c7f3cead1d08802fbaec085806e9472367ba0a6953fd8e1cdeec093d6dd8130"},"schema_version":"1.0","source":{"id":"2604.00784","kind":"arxiv","version":2}},"canonical_sha256":"7090930a9ecb9195d1c86d573a41ef1541514295d1e1ed18fe696316e7fbedf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7090930a9ecb9195d1c86d573a41ef1541514295d1e1ed18fe696316e7fbedf8","first_computed_at":"2026-06-29T01:15:04.714744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:15:04.714744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BellzGhnF6GAkG2SZ+Uh/0LAoAgaktikQuP7xvF0pBByNGpIIsLTI5OA4v1ORFZeMrAxCkpX0M9X4fS1BGHfCQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:15:04.715221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.00784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1bcfd0c87f0a4f3a0b04aa34e76218cbd44b97547bb37bf4ff611455d54c70f","sha256:103666ee3e94aa8aabd2e1d419102d6a34576720a5502e6024cf3d367eba1576"],"state_sha256":"d0202958c65ea9a9ae959f4b279f865aa9043c547c927593c2733c2b856c8310"}