{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q5BPFQLCHFXRRDFC5AQWWHLOGQ","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":"018dd5e2d274d21743ee41e8226d3afc691ac1cd23f2def1a0b3a60204784ae0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T20:21:34Z","title_canon_sha256":"7e824eaacba1115d6278db4c95621346a6e9cb78e486bc73bafe31da13b7a9ca"},"schema_version":"1.0","source":{"id":"2605.11208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11208","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11208v2","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11208","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"Q5BPFQLCHFXR","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"Q5BPFQLCHFXRRDFC","created_at":"2026-05-20T00:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"Q5BPFQLC","created_at":"2026-05-20T00:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:1bf37a8943d80828a35de2d9c967464b931eed672b4f0dfe46a4b4b9febb04d8","target":"graph","created_at":"2026-05-20T00:03:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments show our approach achieves the best overall performance, with consistent gains over strong Multimodal Large Language Model (MLLM) baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 214 simulated surgical videos paired with surgeon-authored reports are sufficiently representative of real clinical procedures and that the Sur40k pretraining on public videos transfers without major domain shift to the target benchmark."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Hi-GaTA is a gated temporal pyramid adapter that aggregates multi-scale video features via text-conditioned cross-attention and gated fusion to enable LLM-based surgical report generation, backed by a new 214-video benchmark and Sur40k pretrained encoder."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports."}],"snapshot_sha256":"195ab86342fc0e850e2360ba10350cdb3e4afbd27c0b8d5621b62ffa2ef45d78"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"be8983cace3537f2a4000a1ab10e73b2ec537050390081a05ed4be42f8bb75a4"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T12:40:20.852162Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T10:01:17.508128Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T08:40:18.203083Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.11208/integrity.json","findings":[],"snapshot_sha256":"fab9db08e000c3166f00da36f62109f2ac446b860a6c0536fc0bd24aefd5a806","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain challenging due to the difficulty of aligning dense spatio-temporal video representations with language-based reasoning and the scarcity of high-quality, privacy-preserving datasets. To address this gap, we establish a benchmark comprising 214 high-quality simulated surgical videos paired with surgeon-authored evaluation reports. Building on this resource, we propose a Perception-Alignment-Reasoning framework for surgical video report generation, fe","authors_text":"Chaohui Dang, James Glasbey, Kedi Sun, Le Zhang, Theodoros N. Arvanitis, Yue Feng","cross_cats":[],"headline":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T20:21:34Z","title":"Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11208","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T06:56:11.707880Z","id":"7faaf6e1-465c-4a6b-812c-1a78471c02fd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Hi-GaTA is a gated temporal pyramid adapter that aggregates multi-scale video features via text-conditioned cross-attention and gated fusion to enable LLM-based surgical report generation, backed by a new 214-video benchmark and Sur40k pretrained encoder.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports.","strongest_claim":"Experiments show our approach achieves the best overall performance, with consistent gains over strong Multimodal Large Language Model (MLLM) baselines.","weakest_assumption":"The 214 simulated surgical videos paired with surgeon-authored reports are sufficiently representative of real clinical procedures and that the Sur40k pretraining on public videos transfers without major domain shift to the target benchmark."}},"verdict_id":"7faaf6e1-465c-4a6b-812c-1a78471c02fd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55acc30a86d9e8698802b35e9a0555520800cda8d31561732f977c45c0fce76b","target":"record","created_at":"2026-05-20T00:03:17Z","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":"018dd5e2d274d21743ee41e8226d3afc691ac1cd23f2def1a0b3a60204784ae0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T20:21:34Z","title_canon_sha256":"7e824eaacba1115d6278db4c95621346a6e9cb78e486bc73bafe31da13b7a9ca"},"schema_version":"1.0","source":{"id":"2605.11208","kind":"arxiv","version":2}},"canonical_sha256":"8742f2c162396f188ca2e8216b1d6e343a25d48a8f6c2113d03725524cbde68d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8742f2c162396f188ca2e8216b1d6e343a25d48a8f6c2113d03725524cbde68d","first_computed_at":"2026-05-20T00:03:17.398055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:17.398055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l2BPshn1eNp7CSsFL1y0Loptkx7eB7uXE6XmlmdsJ7kxUaGbtCJDFtwPThSNQ714RVBHlqGUQSeqP0bYztw+Cg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:17.398872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55acc30a86d9e8698802b35e9a0555520800cda8d31561732f977c45c0fce76b","sha256:1bf37a8943d80828a35de2d9c967464b931eed672b4f0dfe46a4b4b9febb04d8"],"state_sha256":"2596c01c624476f4f872f0dc479b05ead30583bed1c176032987236e02d8f4a1"}