{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OEGY4IESYHERBUFIRRMUVMZQIT","short_pith_number":"pith:OEGY4IES","schema_version":"1.0","canonical_sha256":"710d8e2092c1c910d0a88c594ab33044f2ef58628a1ece9a8a99385b46f350c2","source":{"kind":"arxiv","id":"2506.00717","version":2},"attestation_state":"computed","paper":{"title":"Vid2Coach: Transforming How-To Videos into Task Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Amy Pavel, Kristen Grauman, Kumar Ashutosh, Mina Huh, Ujjaini Das, Zihui Xue","submitted_at":"2025-05-31T21:28:50Z","abstract_excerpt":"People use videos to learn new recipes, exercises, and crafts. Such videos remain difficult for blind and low vision (BLV) people to follow as they rely on visual comparison. Our observations of visual rehabilitation therapists (VRTs) guiding BLV people to follow how-to videos revealed that VRTs provide both proactive and responsive support including detailed descriptions, non-visual workarounds, and progress feedback. We propose Vid2Coach, a system that transforms how-to videos into wearable camera-based assistants that provide accessible instructions and mixed-initiative feedback. From the v"},"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":"2506.00717","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-05-31T21:28:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"12fb36a911096ff7eca893ab904e65a46cb772d886133c082df8e1fea4b37786","abstract_canon_sha256":"4ad9bd75446260a6884c472e6336bd3b7740538d717f501e39c9f034962604ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:12.328651Z","signature_b64":"/LT7fXyh2N9st2Me56hliWOiky+Sf7qhD4gt0RG4Nq1ZHGy1hzjkRblnQ1rLRI6ZyYUeHEIUdmTcm/YVuyDODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"710d8e2092c1c910d0a88c594ab33044f2ef58628a1ece9a8a99385b46f350c2","last_reissued_at":"2026-07-05T11:43:12.327994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:12.327994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vid2Coach: Transforming How-To Videos into Task Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Amy Pavel, Kristen Grauman, Kumar Ashutosh, Mina Huh, Ujjaini Das, Zihui Xue","submitted_at":"2025-05-31T21:28:50Z","abstract_excerpt":"People use videos to learn new recipes, exercises, and crafts. Such videos remain difficult for blind and low vision (BLV) people to follow as they rely on visual comparison. Our observations of visual rehabilitation therapists (VRTs) guiding BLV people to follow how-to videos revealed that VRTs provide both proactive and responsive support including detailed descriptions, non-visual workarounds, and progress feedback. We propose Vid2Coach, a system that transforms how-to videos into wearable camera-based assistants that provide accessible instructions and mixed-initiative feedback. From the v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00717","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/2506.00717/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":"2506.00717","created_at":"2026-07-05T11:43:12.328071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00717v2","created_at":"2026-07-05T11:43:12.328071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00717","created_at":"2026-07-05T11:43:12.328071+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEGY4IESYHER","created_at":"2026-07-05T11:43:12.328071+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEGY4IESYHERBUFI","created_at":"2026-07-05T11:43:12.328071+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEGY4IES","created_at":"2026-07-05T11:43:12.328071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.19629","citing_title":"SkillSight: Efficient First-Person Skill Assessment with Gaze","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10466","citing_title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT","json":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT.json","graph_json":"https://pith.science/api/pith-number/OEGY4IESYHERBUFIRRMUVMZQIT/graph.json","events_json":"https://pith.science/api/pith-number/OEGY4IESYHERBUFIRRMUVMZQIT/events.json","paper":"https://pith.science/paper/OEGY4IES"},"agent_actions":{"view_html":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT","download_json":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT.json","view_paper":"https://pith.science/paper/OEGY4IES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00717&json=true","fetch_graph":"https://pith.science/api/pith-number/OEGY4IESYHERBUFIRRMUVMZQIT/graph.json","fetch_events":"https://pith.science/api/pith-number/OEGY4IESYHERBUFIRRMUVMZQIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT/action/storage_attestation","attest_author":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT/action/author_attestation","sign_citation":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT/action/citation_signature","submit_replication":"https://pith.science/pith/OEGY4IESYHERBUFIRRMUVMZQIT/action/replication_record"}},"created_at":"2026-07-05T11:43:12.328071+00:00","updated_at":"2026-07-05T11:43:12.328071+00:00"}