{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3QC64CE6H6OCYUXHKKGKN6WRX7","short_pith_number":"pith:3QC64CE6","schema_version":"1.0","canonical_sha256":"dc05ee089e3f9c2c52e7528ca6fad1bff7aef284dfa89252a6c928b22ee9d902","source":{"kind":"arxiv","id":"2110.01770","version":2},"attestation_state":"computed","paper":{"title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Jiebo Luo, Jing Bi","submitted_at":"2021-10-05T01:06:53Z","abstract_excerpt":"Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in real-life videos. In contrast to conventional action recognition, goal-directed actions are based on expectations of their outcomes requiring causal knowledge of potential consequences of actions. Thus, integrating the environment structure with goals is critical for solving this task. Previous works learn a single world model will fail to distinguish various "},"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":"2110.01770","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-05T01:06:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"410dd6edc8ca1e7a592bcc17befcf3b639ee5b24e7a4413f922fd6b648047323","abstract_canon_sha256":"7a552edf42e235869c6f16ad5329945e330f376b50247c8928f6cabee88414f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:14.862817Z","signature_b64":"BzlPDv4PUDQ89dvcRQavUOn0QTlKV84ss/gKsKOQTiNXXW7cmnSaI67suMCPnoJScIU/b4UHcpR/QK+0NJmyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc05ee089e3f9c2c52e7528ca6fad1bff7aef284dfa89252a6c928b22ee9d902","last_reissued_at":"2026-07-05T03:21:14.862405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:14.862405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Jiebo Luo, Jing Bi","submitted_at":"2021-10-05T01:06:53Z","abstract_excerpt":"Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in real-life videos. In contrast to conventional action recognition, goal-directed actions are based on expectations of their outcomes requiring causal knowledge of potential consequences of actions. Thus, integrating the environment structure with goals is critical for solving this task. Previous works learn a single world model will fail to distinguish various "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01770","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/2110.01770/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":"2110.01770","created_at":"2026-07-05T03:21:14.862471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.01770v2","created_at":"2026-07-05T03:21:14.862471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01770","created_at":"2026-07-05T03:21:14.862471+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QC64CE6H6OC","created_at":"2026-07-05T03:21:14.862471+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QC64CE6H6OCYUXH","created_at":"2026-07-05T03:21:14.862471+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QC64CE6","created_at":"2026-07-05T03:21:14.862471+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/3QC64CE6H6OCYUXHKKGKN6WRX7","json":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7.json","graph_json":"https://pith.science/api/pith-number/3QC64CE6H6OCYUXHKKGKN6WRX7/graph.json","events_json":"https://pith.science/api/pith-number/3QC64CE6H6OCYUXHKKGKN6WRX7/events.json","paper":"https://pith.science/paper/3QC64CE6"},"agent_actions":{"view_html":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7","download_json":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7.json","view_paper":"https://pith.science/paper/3QC64CE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.01770&json=true","fetch_graph":"https://pith.science/api/pith-number/3QC64CE6H6OCYUXHKKGKN6WRX7/graph.json","fetch_events":"https://pith.science/api/pith-number/3QC64CE6H6OCYUXHKKGKN6WRX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7/action/storage_attestation","attest_author":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7/action/author_attestation","sign_citation":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7/action/citation_signature","submit_replication":"https://pith.science/pith/3QC64CE6H6OCYUXHKKGKN6WRX7/action/replication_record"}},"created_at":"2026-07-05T03:21:14.862471+00:00","updated_at":"2026-07-05T03:21:14.862471+00:00"}