{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UQDDULOWSE6XBOCDOSI3E2XYI2","short_pith_number":"pith:UQDDULOW","schema_version":"1.0","canonical_sha256":"a4063a2dd6913d70b8437491b26af846889c7d032f54092722980fd967947aeb","source":{"kind":"arxiv","id":"2502.04144","version":2},"attestation_state":"computed","paper":{"title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmad Darkhalil, Bin Zhu, Davide Moltisanti, Dima Damen, Fahd Abdelazim, Hazel Doughty, Jacob Chalk, Kaiting Liu, Kevin Flanagan, Kranti Parida, Michael Wray, Omar Emara, Prajwal Gatti, Rhodri Guerrier, Sam Pollard, Saptarshi Sinha, Siddhant Bansal, Toby Perrett, Zhifan Zhu","submitted_at":"2025-02-06T15:25:05Z","abstract_excerpt":"We present a validation dataset of newly-collected kitchen-based egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those i"},"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":"2502.04144","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T15:25:05Z","cross_cats_sorted":[],"title_canon_sha256":"e89fef66aa3982ff396a665ef85c575cddf724eb652090e31e3231fb35908fb7","abstract_canon_sha256":"15d794bce1d607745f3dd12c4cffc7c0f751660976bf92c5a22b7e2cfbc522bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:42.275938Z","signature_b64":"YrNtYH4crt278y6DwfdMbBEBfGIbDjmMGCzdxxYNqASWY59Uusv+nYxWTzyEhbJPZ3Df1NyQqF/BwWdgAXZlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4063a2dd6913d70b8437491b26af846889c7d032f54092722980fd967947aeb","last_reissued_at":"2026-07-05T10:38:42.275490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:42.275490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmad Darkhalil, Bin Zhu, Davide Moltisanti, Dima Damen, Fahd Abdelazim, Hazel Doughty, Jacob Chalk, Kaiting Liu, Kevin Flanagan, Kranti Parida, Michael Wray, Omar Emara, Prajwal Gatti, Rhodri Guerrier, Sam Pollard, Saptarshi Sinha, Siddhant Bansal, Toby Perrett, Zhifan Zhu","submitted_at":"2025-02-06T15:25:05Z","abstract_excerpt":"We present a validation dataset of newly-collected kitchen-based egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04144","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/2502.04144/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":"2502.04144","created_at":"2026-07-05T10:38:42.275541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04144v2","created_at":"2026-07-05T10:38:42.275541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04144","created_at":"2026-07-05T10:38:42.275541+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQDDULOWSE6X","created_at":"2026-07-05T10:38:42.275541+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQDDULOWSE6XBOCD","created_at":"2026-07-05T10:38:42.275541+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQDDULOW","created_at":"2026-07-05T10:38:42.275541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31557","citing_title":"EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08342","citing_title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2","json":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2.json","graph_json":"https://pith.science/api/pith-number/UQDDULOWSE6XBOCDOSI3E2XYI2/graph.json","events_json":"https://pith.science/api/pith-number/UQDDULOWSE6XBOCDOSI3E2XYI2/events.json","paper":"https://pith.science/paper/UQDDULOW"},"agent_actions":{"view_html":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2","download_json":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2.json","view_paper":"https://pith.science/paper/UQDDULOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04144&json=true","fetch_graph":"https://pith.science/api/pith-number/UQDDULOWSE6XBOCDOSI3E2XYI2/graph.json","fetch_events":"https://pith.science/api/pith-number/UQDDULOWSE6XBOCDOSI3E2XYI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2/action/storage_attestation","attest_author":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2/action/author_attestation","sign_citation":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2/action/citation_signature","submit_replication":"https://pith.science/pith/UQDDULOWSE6XBOCDOSI3E2XYI2/action/replication_record"}},"created_at":"2026-07-05T10:38:42.275541+00:00","updated_at":"2026-07-05T10:38:42.275541+00:00"}