{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B77TQLL25GO25MR76EHTZVEJII","short_pith_number":"pith:B77TQLL2","schema_version":"1.0","canonical_sha256":"0fff382d7ae99daeb23ff10f3cd489423f52be7b8c12f77851eb8389ed69b24d","source":{"kind":"arxiv","id":"2403.18600","version":2},"attestation_state":"computed","paper":{"title":"RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ali Zare, Hammad Ayyubi, Shih-Fu Chang, Yulei Niu","submitted_at":"2024-03-27T14:22:40Z","abstract_excerpt":"Procedure Planning in instructional videos entails generating a sequence of action steps based on visual observations of the initial and target states. Despite the rapid progress in this task, there remain several critical challenges to be solved: (1) Adaptive procedures: Prior works hold an unrealistic assumption that the number of action steps is known and fixed, leading to non-generalizable models in real-world scenarios where the sequence length varies. (2) Temporal relation: Understanding the step temporal relation knowledge is essential in producing reasonable and executable plans. (3) A"},"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":"2403.18600","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T14:22:40Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"dc0df2fd04314dc6310314ee371085d263a7441aac789c408866b3fd10ee3cae","abstract_canon_sha256":"26ada3f3ed7f0939b81bafcaa4e06adc130b9980d0b88ec21cbdf9c8654a0bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:25.337705Z","signature_b64":"mL97v0tvReYSnk6iMxTASf9W2aYl6qgnVyzNlJPePBO9UD1eIhlj8shK3qOc6Mutwvnh926QEqEh5JZBz25sCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fff382d7ae99daeb23ff10f3cd489423f52be7b8c12f77851eb8389ed69b24d","last_reissued_at":"2026-07-05T09:11:25.337187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:25.337187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAP: Retrieval-Augmented Planner for Adaptive Procedure Planning in Instructional Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ali Zare, Hammad Ayyubi, Shih-Fu Chang, Yulei Niu","submitted_at":"2024-03-27T14:22:40Z","abstract_excerpt":"Procedure Planning in instructional videos entails generating a sequence of action steps based on visual observations of the initial and target states. Despite the rapid progress in this task, there remain several critical challenges to be solved: (1) Adaptive procedures: Prior works hold an unrealistic assumption that the number of action steps is known and fixed, leading to non-generalizable models in real-world scenarios where the sequence length varies. (2) Temporal relation: Understanding the step temporal relation knowledge is essential in producing reasonable and executable plans. (3) A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18600","kind":"arxiv","version":2},"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/2403.18600/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":"2403.18600","created_at":"2026-07-05T09:11:25.337250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18600v2","created_at":"2026-07-05T09:11:25.337250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18600","created_at":"2026-07-05T09:11:25.337250+00:00"},{"alias_kind":"pith_short_12","alias_value":"B77TQLL25GO2","created_at":"2026-07-05T09:11:25.337250+00:00"},{"alias_kind":"pith_short_16","alias_value":"B77TQLL25GO25MR7","created_at":"2026-07-05T09:11:25.337250+00:00"},{"alias_kind":"pith_short_8","alias_value":"B77TQLL2","created_at":"2026-07-05T09:11:25.337250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15130","citing_title":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII","json":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII.json","graph_json":"https://pith.science/api/pith-number/B77TQLL25GO25MR76EHTZVEJII/graph.json","events_json":"https://pith.science/api/pith-number/B77TQLL25GO25MR76EHTZVEJII/events.json","paper":"https://pith.science/paper/B77TQLL2"},"agent_actions":{"view_html":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII","download_json":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII.json","view_paper":"https://pith.science/paper/B77TQLL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18600&json=true","fetch_graph":"https://pith.science/api/pith-number/B77TQLL25GO25MR76EHTZVEJII/graph.json","fetch_events":"https://pith.science/api/pith-number/B77TQLL25GO25MR76EHTZVEJII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII/action/storage_attestation","attest_author":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII/action/author_attestation","sign_citation":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII/action/citation_signature","submit_replication":"https://pith.science/pith/B77TQLL25GO25MR76EHTZVEJII/action/replication_record"}},"created_at":"2026-07-05T09:11:25.337250+00:00","updated_at":"2026-07-05T09:11:25.337250+00:00"}