{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CLIS63Q7G4VAUOSY2ZUPZZQR7Y","short_pith_number":"pith:CLIS63Q7","schema_version":"1.0","canonical_sha256":"12d12f6e1f372a0a3a58d668fce611fe283f0e88702d06551c20395807280f82","source":{"kind":"arxiv","id":"2312.14556","version":4},"attestation_state":"computed","paper":{"title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akshay Vyas, Bharath Challa, Bhavya Gouripeddi, Eric Ragan, Jikai Wang, Likhitha Pallapothula, Nicholas Ruozzi, Qifan Zhang, Rohith Peddi, Shivvrat Arya, Vasundhara Komaragiri, Vibhav Gogate, Yu Xiang","submitted_at":"2023-12-22T09:29:45Z","abstract_excerpt":"Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furniture or preparing a recipe. However, the complexity and duration of procedural activities inherently increase the likelihood of making errors. Understanding such procedural activities from a sequence of frames is a challenging task that demands an accurate interpretation of visual information and the ability to reason about the structure of the activ"},"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":"2312.14556","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T09:29:45Z","cross_cats_sorted":[],"title_canon_sha256":"71e4aefff1671ad5262cda85edea4329585d3df8274d1a66eac563f8c9d78955","abstract_canon_sha256":"6518fb05e3f9f431d9ebe30f800339d76167dc45afb56b7d0c759cb39a1fdb67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:42.749628Z","signature_b64":"zM1gWOZU2GnLrupIY+Acn+an4ciiVyFJna8RnVntgPvXqC6LTWnkf4bSVim2kI0k6rJ63qAv3uuAsjTXPcVbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d12f6e1f372a0a3a58d668fce611fe283f0e88702d06551c20395807280f82","last_reissued_at":"2026-07-05T09:45:42.749125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:42.749125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akshay Vyas, Bharath Challa, Bhavya Gouripeddi, Eric Ragan, Jikai Wang, Likhitha Pallapothula, Nicholas Ruozzi, Qifan Zhang, Rohith Peddi, Shivvrat Arya, Vasundhara Komaragiri, Vibhav Gogate, Yu Xiang","submitted_at":"2023-12-22T09:29:45Z","abstract_excerpt":"Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furniture or preparing a recipe. However, the complexity and duration of procedural activities inherently increase the likelihood of making errors. Understanding such procedural activities from a sequence of frames is a challenging task that demands an accurate interpretation of visual information and the ability to reason about the structure of the activ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14556","kind":"arxiv","version":4},"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/2312.14556/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":"2312.14556","created_at":"2026-07-05T09:45:42.749183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14556v4","created_at":"2026-07-05T09:45:42.749183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14556","created_at":"2026-07-05T09:45:42.749183+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLIS63Q7G4VA","created_at":"2026-07-05T09:45:42.749183+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLIS63Q7G4VAUOSY","created_at":"2026-07-05T09:45:42.749183+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLIS63Q7","created_at":"2026-07-05T09:45:42.749183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25317","citing_title":"ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10936","citing_title":"Personal Visual Context Learning in Large Multimodal Models","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y","json":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y.json","graph_json":"https://pith.science/api/pith-number/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/graph.json","events_json":"https://pith.science/api/pith-number/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/events.json","paper":"https://pith.science/paper/CLIS63Q7"},"agent_actions":{"view_html":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y","download_json":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y.json","view_paper":"https://pith.science/paper/CLIS63Q7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14556&json=true","fetch_graph":"https://pith.science/api/pith-number/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/action/storage_attestation","attest_author":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/action/author_attestation","sign_citation":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/action/citation_signature","submit_replication":"https://pith.science/pith/CLIS63Q7G4VAUOSY2ZUPZZQR7Y/action/replication_record"}},"created_at":"2026-07-05T09:45:42.749183+00:00","updated_at":"2026-07-05T09:45:42.749183+00:00"}