{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UPBHCMUEWHDETULKFUJF2CCODT","short_pith_number":"pith:UPBHCMUE","schema_version":"1.0","canonical_sha256":"a3c2713284b1c649d16a2d125d084e1cde88fe7a4b0ec33012e3072a563856d6","source":{"kind":"arxiv","id":"2312.03849","version":2},"attestation_state":"computed","paper":{"title":"LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolin Lai, Guan Pang, James M. Rehg, Lawrence Chen, Miao Liu, Xiaoliang Dai","submitted_at":"2023-12-06T19:02:40Z","abstract_excerpt":"Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to synthesize an image depicting an action in the user's context (i.e., action frame) by conditioning on a user prompt and an input egocentric image. Notably, existing egocentric action datasets lack the detailed annotations that describe the execution of actions. Additionally, existing diffusion-based image manipulation models are sub-optimal in controlling the s"},"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":"2312.03849","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T19:02:40Z","cross_cats_sorted":[],"title_canon_sha256":"a0a3faa608c5fa267d820e7559f3f11f1f94751cbed53760994f3d33b1edc7d5","abstract_canon_sha256":"d2c89f30d8e13f8ca9aca4ed01693b4aa86854ba5a04b1fbbc08248c499a77d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:20.171433Z","signature_b64":"rxoEM7X3/9kFYW+f2aq4rFpRCuHa6P7I4uTLj3TcWELr0JJJ6siu7OHcwqLhI0M7TR0mfLtw+dVJf8D7EFaEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3c2713284b1c649d16a2d125d084e1cde88fe7a4b0ec33012e3072a563856d6","last_reissued_at":"2026-07-05T07:59:20.170910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:20.170910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolin Lai, Guan Pang, James M. Rehg, Lawrence Chen, Miao Liu, Xiaoliang Dai","submitted_at":"2023-12-06T19:02:40Z","abstract_excerpt":"Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to synthesize an image depicting an action in the user's context (i.e., action frame) by conditioning on a user prompt and an input egocentric image. Notably, existing egocentric action datasets lack the detailed annotations that describe the execution of actions. Additionally, existing diffusion-based image manipulation models are sub-optimal in controlling the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03849","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/2312.03849/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":"2312.03849","created_at":"2026-07-05T07:59:20.170972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03849v2","created_at":"2026-07-05T07:59:20.170972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03849","created_at":"2026-07-05T07:59:20.170972+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPBHCMUEWHDE","created_at":"2026-07-05T07:59:20.170972+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPBHCMUEWHDETULK","created_at":"2026-07-05T07:59:20.170972+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPBHCMUE","created_at":"2026-07-05T07:59:20.170972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17184","citing_title":"Substantial, Decomposable, and Invisible: Visual Context Misalignment in Instructional Videos for Physical Tasks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT","json":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT.json","graph_json":"https://pith.science/api/pith-number/UPBHCMUEWHDETULKFUJF2CCODT/graph.json","events_json":"https://pith.science/api/pith-number/UPBHCMUEWHDETULKFUJF2CCODT/events.json","paper":"https://pith.science/paper/UPBHCMUE"},"agent_actions":{"view_html":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT","download_json":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT.json","view_paper":"https://pith.science/paper/UPBHCMUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03849&json=true","fetch_graph":"https://pith.science/api/pith-number/UPBHCMUEWHDETULKFUJF2CCODT/graph.json","fetch_events":"https://pith.science/api/pith-number/UPBHCMUEWHDETULKFUJF2CCODT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/action/storage_attestation","attest_author":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/action/author_attestation","sign_citation":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/action/citation_signature","submit_replication":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/action/replication_record"}},"created_at":"2026-07-05T07:59:20.170972+00:00","updated_at":"2026-07-05T07:59:20.170972+00:00"}