{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FQHUGGCMU65UK4HW56INZMEY3U","short_pith_number":"pith:FQHUGGCM","schema_version":"1.0","canonical_sha256":"2c0f43184ca7bb4570f6ef90dcb098dd18ddf8b0788a3f7abaa95c39244cfc95","source":{"kind":"arxiv","id":"2607.29401","version":1},"attestation_state":"computed","paper":{"title":"OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Guanchao Tong, Jiaqi Xuan, Lei Zhang, Meimei Zhang, Shuaiwu Dong, Sijia Zhou, Yingda Yu, Yuehan Shi, Zhentong Ye","submitted_at":"2026-07-31T13:21:31Z","abstract_excerpt":"Video Scene Procedure Planning (VSPP) supplies the target start-goal observations in advance, leaving open how a planner should act when the evidence must itself be retrieved. We introduce Cross-Video Scene Procedure Planning (CVSPP): given an answer-redacted start-goal query and K candidate videos, a model must retrieve the supporting video, localize the relevant window, and predict the action sequence. Two obstacles couple here. Same-task demonstrations share stages and windows, and an early hard selection passes the wrong scene chain to the planner. We build an eleven-source benchmark with "},"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":"2607.29401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T13:21:31Z","cross_cats_sorted":[],"title_canon_sha256":"257434d199bfc6f41c008074656faafa9dcec438fe094c6dad216dd1de31f967","abstract_canon_sha256":"809234b89c8d37c9d23efc9dd49429f09aaf8eace80f001b5bf10fe8935ff549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:33:37.673151Z","signature_b64":"RSH2lgVVyrJgrWk4htN8wYmHUXVxnMs6X8oQszAh1Avr6HDMcWtqFFCGV+MvRCZ6x0KVl9ANk7opGLBmQd4oAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c0f43184ca7bb4570f6ef90dcb098dd18ddf8b0788a3f7abaa95c39244cfc95","last_reissued_at":"2026-08-03T01:33:37.671537Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:33:37.671537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Guanchao Tong, Jiaqi Xuan, Lei Zhang, Meimei Zhang, Shuaiwu Dong, Sijia Zhou, Yingda Yu, Yuehan Shi, Zhentong Ye","submitted_at":"2026-07-31T13:21:31Z","abstract_excerpt":"Video Scene Procedure Planning (VSPP) supplies the target start-goal observations in advance, leaving open how a planner should act when the evidence must itself be retrieved. We introduce Cross-Video Scene Procedure Planning (CVSPP): given an answer-redacted start-goal query and K candidate videos, a model must retrieve the supporting video, localize the relevant window, and predict the action sequence. Two obstacles couple here. Same-task demonstrations share stages and windows, and an early hard selection passes the wrong scene chain to the planner. We build an eleven-source benchmark with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29401","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/2607.29401/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":"2607.29401","created_at":"2026-08-03T01:33:37.672440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29401v1","created_at":"2026-08-03T01:33:37.672440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29401","created_at":"2026-08-03T01:33:37.672440+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQHUGGCMU65U","created_at":"2026-08-03T01:33:37.672440+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQHUGGCMU65UK4HW","created_at":"2026-08-03T01:33:37.672440+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQHUGGCM","created_at":"2026-08-03T01:33:37.672440+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/FQHUGGCMU65UK4HW56INZMEY3U","json":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U.json","graph_json":"https://pith.science/api/pith-number/FQHUGGCMU65UK4HW56INZMEY3U/graph.json","events_json":"https://pith.science/api/pith-number/FQHUGGCMU65UK4HW56INZMEY3U/events.json","paper":"https://pith.science/paper/FQHUGGCM"},"agent_actions":{"view_html":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U","download_json":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U.json","view_paper":"https://pith.science/paper/FQHUGGCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29401&json=true","fetch_graph":"https://pith.science/api/pith-number/FQHUGGCMU65UK4HW56INZMEY3U/graph.json","fetch_events":"https://pith.science/api/pith-number/FQHUGGCMU65UK4HW56INZMEY3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U/action/storage_attestation","attest_author":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U/action/author_attestation","sign_citation":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U/action/citation_signature","submit_replication":"https://pith.science/pith/FQHUGGCMU65UK4HW56INZMEY3U/action/replication_record"}},"created_at":"2026-08-03T01:33:37.672440+00:00","updated_at":"2026-08-03T01:33:37.672440+00:00"}