{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FUM3KYGITTOSLNGL7Y3AJWSUL7","short_pith_number":"pith:FUM3KYGI","schema_version":"1.0","canonical_sha256":"2d19b560c89cdd25b4cbfe3604da545ff017e29c4d7bfe643dc71f9380cf58dd","source":{"kind":"arxiv","id":"2308.08885","version":1},"attestation_state":"computed","paper":{"title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Lan Wang, Jia-Run Du, Jingke Meng, Kun-Yu Lin, Wei-Shi Zheng","submitted_at":"2023-08-17T09:43:28Z","abstract_excerpt":"In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state. A critical challenge of this task is the large semantic gap between observed visual states and unobserved intermediate actions, which is ignored by previous works. Specifically, this semantic gap refers to that the contents in the observed visual states are semantically different from the elements of some action text labels in a procedure. To bridge this semantic gap, we propo"},"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":"2308.08885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-17T09:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"86fbace4e2710c1547becf95fc6dd81c5550785169053c09805910571cd65c87","abstract_canon_sha256":"cfc388fca4453494ba5adafeee538608d23a6a06cf3a10f0831aa0e82b8b9798"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:13.055845Z","signature_b64":"96eblMeacFHPHXT6e3H+QtXyJvWrcm8gQQXg1bC3JVexYmj+gBWZRuGMK1RotBj55/SbunO7l4JR+myqMzr5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d19b560c89cdd25b4cbfe3604da545ff017e29c4d7bfe643dc71f9380cf58dd","last_reissued_at":"2026-07-05T06:42:13.055339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:13.055339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An-Lan Wang, Jia-Run Du, Jingke Meng, Kun-Yu Lin, Wei-Shi Zheng","submitted_at":"2023-08-17T09:43:28Z","abstract_excerpt":"In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state. A critical challenge of this task is the large semantic gap between observed visual states and unobserved intermediate actions, which is ignored by previous works. Specifically, this semantic gap refers to that the contents in the observed visual states are semantically different from the elements of some action text labels in a procedure. To bridge this semantic gap, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08885","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/2308.08885/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":"2308.08885","created_at":"2026-07-05T06:42:13.055417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08885v1","created_at":"2026-07-05T06:42:13.055417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08885","created_at":"2026-07-05T06:42:13.055417+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUM3KYGITTOS","created_at":"2026-07-05T06:42:13.055417+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUM3KYGITTOSLNGL","created_at":"2026-07-05T06:42:13.055417+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUM3KYGI","created_at":"2026-07-05T06:42:13.055417+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/FUM3KYGITTOSLNGL7Y3AJWSUL7","json":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7.json","graph_json":"https://pith.science/api/pith-number/FUM3KYGITTOSLNGL7Y3AJWSUL7/graph.json","events_json":"https://pith.science/api/pith-number/FUM3KYGITTOSLNGL7Y3AJWSUL7/events.json","paper":"https://pith.science/paper/FUM3KYGI"},"agent_actions":{"view_html":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7","download_json":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7.json","view_paper":"https://pith.science/paper/FUM3KYGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08885&json=true","fetch_graph":"https://pith.science/api/pith-number/FUM3KYGITTOSLNGL7Y3AJWSUL7/graph.json","fetch_events":"https://pith.science/api/pith-number/FUM3KYGITTOSLNGL7Y3AJWSUL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7/action/storage_attestation","attest_author":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7/action/author_attestation","sign_citation":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7/action/citation_signature","submit_replication":"https://pith.science/pith/FUM3KYGITTOSLNGL7Y3AJWSUL7/action/replication_record"}},"created_at":"2026-07-05T06:42:13.055417+00:00","updated_at":"2026-07-05T06:42:13.055417+00:00"}