{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K7QLN5J2UIBAQVB5ZKTASPAWWZ","short_pith_number":"pith:K7QLN5J2","schema_version":"1.0","canonical_sha256":"57e0b6f53aa20208543dcaa6093c16b66953eeb77038ec69369d801249b4ee36","source":{"kind":"arxiv","id":"2406.01486","version":3},"attestation_state":"computed","paper":{"title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Giovanni Maria Farinella, Luigi Seminara","submitted_at":"2024-06-03T16:11:39Z","abstract_excerpt":"Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-understandable representation of procedural activities, encoding a partial ordering over the key-steps. While previous works generally relied on hand-crafted procedures to extract task graphs from videos, in this paper, we propose an approach based on direct maximum likelihood optimization of edges' weights, which allows gradient-based learning of task graphs and can be naturally p"},"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":"2406.01486","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T16:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"4a97a5e69554f33933c0edf75dac2b4ba731c6b0857638653c21e0ca0ac416a8","abstract_canon_sha256":"2931df5d1412719be79e3f89850d8d133f7dd4d43c7234c11989c73bec1a38af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:58.560518Z","signature_b64":"6gyyS7IR/6u18EFbepu0PVA9raBpHQGS+FZCxtkaax5B+nJRZF0E1FjgEqsXFzmv+0ptzw5CuCIQ1nCGg21YCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57e0b6f53aa20208543dcaa6093c16b66953eeb77038ec69369d801249b4ee36","last_reissued_at":"2026-07-05T09:58:58.560040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:58.560040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Giovanni Maria Farinella, Luigi Seminara","submitted_at":"2024-06-03T16:11:39Z","abstract_excerpt":"Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-understandable representation of procedural activities, encoding a partial ordering over the key-steps. While previous works generally relied on hand-crafted procedures to extract task graphs from videos, in this paper, we propose an approach based on direct maximum likelihood optimization of edges' weights, which allows gradient-based learning of task graphs and can be naturally p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01486","kind":"arxiv","version":3},"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/2406.01486/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":"2406.01486","created_at":"2026-07-05T09:58:58.560103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01486v3","created_at":"2026-07-05T09:58:58.560103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01486","created_at":"2026-07-05T09:58:58.560103+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7QLN5J2UIBA","created_at":"2026-07-05T09:58:58.560103+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7QLN5J2UIBAQVB5","created_at":"2026-07-05T09:58:58.560103+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7QLN5J2","created_at":"2026-07-05T09:58:58.560103+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/K7QLN5J2UIBAQVB5ZKTASPAWWZ","json":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ.json","graph_json":"https://pith.science/api/pith-number/K7QLN5J2UIBAQVB5ZKTASPAWWZ/graph.json","events_json":"https://pith.science/api/pith-number/K7QLN5J2UIBAQVB5ZKTASPAWWZ/events.json","paper":"https://pith.science/paper/K7QLN5J2"},"agent_actions":{"view_html":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ","download_json":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ.json","view_paper":"https://pith.science/paper/K7QLN5J2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01486&json=true","fetch_graph":"https://pith.science/api/pith-number/K7QLN5J2UIBAQVB5ZKTASPAWWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/K7QLN5J2UIBAQVB5ZKTASPAWWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ/action/storage_attestation","attest_author":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ/action/author_attestation","sign_citation":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ/action/citation_signature","submit_replication":"https://pith.science/pith/K7QLN5J2UIBAQVB5ZKTASPAWWZ/action/replication_record"}},"created_at":"2026-07-05T09:58:58.560103+00:00","updated_at":"2026-07-05T09:58:58.560103+00:00"}