{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WAFVJ4L3FER27RYNXXWDIG5D7N","short_pith_number":"pith:WAFVJ4L3","schema_version":"1.0","canonical_sha256":"b00b54f17b2923afc70dbdec341ba3fb663892aa328d4981e6296f238c55e135","source":{"kind":"arxiv","id":"2606.17279","version":1},"attestation_state":"computed","paper":{"title":"Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhang, Mathias Unberath, Yiqing Shen","submitted_at":"2026-06-15T20:40:45Z","abstract_excerpt":"Surgical video question answering requires multi-step reasoning across semantic, spatial, and temporal dimensions. Existing methods architecturally compress videos into discrete token representations and couple visual perception with reasoning. This approach fragments continuous spatial-temporal relationships and has been shown to restrict multi-step reasoning capabilities. We introduce a reinforcement learning (RL) framework that trains large language models (LLMs) to decouple perception from reasoning by operating over digital twin representations constructed from surgical foundation models."},"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":"2606.17279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T20:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"2d92d41c22a3f308fcc56c33f5a0d457f295be98fe854c089588be9fc2b459d2","abstract_canon_sha256":"682979c471383f0a7e7f956db119889e523d2d352c7275546335078b33e0f063"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:07.964218Z","signature_b64":"Q/1naz4m0em+gsnhMtXRsy4Rpx/ey9UUy0JPT2yqCdC9GE1m3NLhBfgx0gQkbjC+sKppLA78kSZ1n3YipMqYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b00b54f17b2923afc70dbdec341ba3fb663892aa328d4981e6296f238c55e135","last_reissued_at":"2026-06-19T16:10:07.963798Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:07.963798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhang, Mathias Unberath, Yiqing Shen","submitted_at":"2026-06-15T20:40:45Z","abstract_excerpt":"Surgical video question answering requires multi-step reasoning across semantic, spatial, and temporal dimensions. Existing methods architecturally compress videos into discrete token representations and couple visual perception with reasoning. This approach fragments continuous spatial-temporal relationships and has been shown to restrict multi-step reasoning capabilities. We introduce a reinforcement learning (RL) framework that trains large language models (LLMs) to decouple perception from reasoning by operating over digital twin representations constructed from surgical foundation models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17279","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/2606.17279/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":"2606.17279","created_at":"2026-06-19T16:10:07.963852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17279v1","created_at":"2026-06-19T16:10:07.963852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17279","created_at":"2026-06-19T16:10:07.963852+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAFVJ4L3FER2","created_at":"2026-06-19T16:10:07.963852+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAFVJ4L3FER27RYN","created_at":"2026-06-19T16:10:07.963852+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAFVJ4L3","created_at":"2026-06-19T16:10:07.963852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N","json":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N.json","graph_json":"https://pith.science/api/pith-number/WAFVJ4L3FER27RYNXXWDIG5D7N/graph.json","events_json":"https://pith.science/api/pith-number/WAFVJ4L3FER27RYNXXWDIG5D7N/events.json","paper":"https://pith.science/paper/WAFVJ4L3"},"agent_actions":{"view_html":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N","download_json":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N.json","view_paper":"https://pith.science/paper/WAFVJ4L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17279&json=true","fetch_graph":"https://pith.science/api/pith-number/WAFVJ4L3FER27RYNXXWDIG5D7N/graph.json","fetch_events":"https://pith.science/api/pith-number/WAFVJ4L3FER27RYNXXWDIG5D7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N/action/storage_attestation","attest_author":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N/action/author_attestation","sign_citation":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N/action/citation_signature","submit_replication":"https://pith.science/pith/WAFVJ4L3FER27RYNXXWDIG5D7N/action/replication_record"}},"created_at":"2026-06-19T16:10:07.963852+00:00","updated_at":"2026-06-19T16:10:07.963852+00:00"}