{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q5BPFQLCHFXRRDFC5AQWWHLOGQ","short_pith_number":"pith:Q5BPFQLC","schema_version":"1.0","canonical_sha256":"8742f2c162396f188ca2e8216b1d6e343a25d48a8f6c2113d03725524cbde68d","source":{"kind":"arxiv","id":"2605.11208","version":2},"attestation_state":"computed","paper":{"title":"Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Dang, James Glasbey, Kedi Sun, Le Zhang, Theodoros N. Arvanitis, Yue Feng","submitted_at":"2026-05-11T20:21:34Z","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"},"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":true},"canonical_record":{"source":{"id":"2605.11208","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T20:21:34Z","cross_cats_sorted":[],"title_canon_sha256":"7e824eaacba1115d6278db4c95621346a6e9cb78e486bc73bafe31da13b7a9ca","abstract_canon_sha256":"018dd5e2d274d21743ee41e8226d3afc691ac1cd23f2def1a0b3a60204784ae0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:17.398872Z","signature_b64":"l2BPshn1eNp7CSsFL1y0Loptkx7eB7uXE6XmlmdsJ7kxUaGbtCJDFtwPThSNQ714RVBHlqGUQSeqP0bYztw+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8742f2c162396f188ca2e8216b1d6e343a25d48a8f6c2113d03725524cbde68d","last_reissued_at":"2026-05-20T00:03:17.398055Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:17.398055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaohui Dang, James Glasbey, Kedi Sun, Le Zhang, Theodoros N. Arvanitis, Yue Feng","submitted_at":"2026-05-11T20:21:34Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show our approach achieves the best overall performance, with consistent gains over strong Multimodal Large Language Model (MLLM) baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"195ab86342fc0e850e2360ba10350cdb3e4afbd27c0b8d5621b62ffa2ef45d78"},"source":{"id":"2605.11208","kind":"arxiv","version":2},"verdict":{"id":"7faaf6e1-465c-4a6b-812c-1a78471c02fd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T06:56:11.707880Z","strongest_claim":"Experiments show our approach achieves the best overall performance, with consistent gains over strong Multimodal Large Language Model (MLLM) baselines.","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","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.","pith_extraction_headline":"A hierarchical adapter compresses long surgical videos into tokens that let language models generate accurate procedure reports."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11208/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"fab9db08e000c3166f00da36f62109f2ac446b860a6c0536fc0bd24aefd5a806"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"be8983cace3537f2a4000a1ab10e73b2ec537050390081a05ed4be42f8bb75a4"},"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":"2605.11208","created_at":"2026-05-20T00:03:17.398167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11208v2","created_at":"2026-05-20T00:03:17.398167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11208","created_at":"2026-05-20T00:03:17.398167+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5BPFQLCHFXR","created_at":"2026-05-20T00:03:17.398167+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5BPFQLCHFXRRDFC","created_at":"2026-05-20T00:03:17.398167+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5BPFQLC","created_at":"2026-05-20T00:03:17.398167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ","json":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ.json","graph_json":"https://pith.science/api/pith-number/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/graph.json","events_json":"https://pith.science/api/pith-number/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/events.json","paper":"https://pith.science/paper/Q5BPFQLC"},"agent_actions":{"view_html":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ","download_json":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ.json","view_paper":"https://pith.science/paper/Q5BPFQLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11208&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/action/storage_attestation","attest_author":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/action/author_attestation","sign_citation":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/action/citation_signature","submit_replication":"https://pith.science/pith/Q5BPFQLCHFXRRDFC5AQWWHLOGQ/action/replication_record"}},"created_at":"2026-05-20T00:03:17.398167+00:00","updated_at":"2026-05-20T00:03:17.398167+00:00"}