{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IFAFO4UZHPYRQDCHTMXFNTLXQD","short_pith_number":"pith:IFAFO4UZ","schema_version":"1.0","canonical_sha256":"41405772993bf1180c479b2e56cd7780d1275131938105adb76941dc5b6b51ae","source":{"kind":"arxiv","id":"2006.13256","version":4},"attestation_state":"computed","paper":{"title":"Rescaling Egocentric Vision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Davide Moltisanti, Dima Damen, Evangelos Kazakos, Giovanni Maria Farinella, Hazel Doughty, Jian Ma, Jonathan Munro, Michael Wray, Toby Perrett, Will Price","submitted_at":"2020-06-23T18:28:04Z","abstract_excerpt":"This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action d"},"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":"2006.13256","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-06-23T18:28:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23e662794700ea6da6cca90f997e0e4cea3a56ade2e191fd1e5efaa212ceb510","abstract_canon_sha256":"384794026ee9da7910cf2dcfefaeb47f4ae7c75c0b1b4e2bdcf19843d28a0545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:07.198646Z","signature_b64":"E+sQlHehe2VL0OH6q+Ku6liRCPUqQQF4v4Wjg68DCWosuVsk49Apnibuqi8EokuJehkdsv1LIHkCzUAufl7jCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41405772993bf1180c479b2e56cd7780d1275131938105adb76941dc5b6b51ae","last_reissued_at":"2026-07-05T03:15:07.198174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:07.198174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rescaling Egocentric Vision","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Davide Moltisanti, Dima Damen, Evangelos Kazakos, Giovanni Maria Farinella, Hazel Doughty, Jian Ma, Jonathan Munro, Michael Wray, Toby Perrett, Will Price","submitted_at":"2020-06-23T18:28:04Z","abstract_excerpt":"This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13256","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/2006.13256/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":"2006.13256","created_at":"2026-07-05T03:15:07.198230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13256v4","created_at":"2026-07-05T03:15:07.198230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13256","created_at":"2026-07-05T03:15:07.198230+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFAFO4UZHPYR","created_at":"2026-07-05T03:15:07.198230+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFAFO4UZHPYRQDCH","created_at":"2026-07-05T03:15:07.198230+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFAFO4UZ","created_at":"2026-07-05T03:15:07.198230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17256","citing_title":"Contrastive Action-Image Pre-training for Visuomotor Control","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2204.00598","citing_title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2307.16125","citing_title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD","json":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD.json","graph_json":"https://pith.science/api/pith-number/IFAFO4UZHPYRQDCHTMXFNTLXQD/graph.json","events_json":"https://pith.science/api/pith-number/IFAFO4UZHPYRQDCHTMXFNTLXQD/events.json","paper":"https://pith.science/paper/IFAFO4UZ"},"agent_actions":{"view_html":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD","download_json":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD.json","view_paper":"https://pith.science/paper/IFAFO4UZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13256&json=true","fetch_graph":"https://pith.science/api/pith-number/IFAFO4UZHPYRQDCHTMXFNTLXQD/graph.json","fetch_events":"https://pith.science/api/pith-number/IFAFO4UZHPYRQDCHTMXFNTLXQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD/action/storage_attestation","attest_author":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD/action/author_attestation","sign_citation":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD/action/citation_signature","submit_replication":"https://pith.science/pith/IFAFO4UZHPYRQDCHTMXFNTLXQD/action/replication_record"}},"created_at":"2026-07-05T03:15:07.198230+00:00","updated_at":"2026-07-05T03:15:07.198230+00:00"}