{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UPBHCMUEWHDETULKFUJF2CCODT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d2c89f30d8e13f8ca9aca4ed01693b4aa86854ba5a04b1fbbc08248c499a77d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T19:02:40Z","title_canon_sha256":"a0a3faa608c5fa267d820e7559f3f11f1f94751cbed53760994f3d33b1edc7d5"},"schema_version":"1.0","source":{"id":"2312.03849","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03849","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03849v2","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03849","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"UPBHCMUEWHDE","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"UPBHCMUEWHDETULK","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"UPBHCMUE","created_at":"2026-07-05T07:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:64a2b67fba29ed326ed057923960f78a4366ae9f29a133ae765a520794276966","target":"graph","created_at":"2026-07-05T07:59:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.03849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bolin Lai, Guan Pang, James M. Rehg, Lawrence Chen, Miao Liu, Xiaoliang Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T19:02:40Z","title":"LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03849","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:18a1e28928fc86fb2b2ee0eaba812f9d5b863b1030470445fd6f98a84fee402f","target":"record","created_at":"2026-07-05T07:59:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d2c89f30d8e13f8ca9aca4ed01693b4aa86854ba5a04b1fbbc08248c499a77d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T19:02:40Z","title_canon_sha256":"a0a3faa608c5fa267d820e7559f3f11f1f94751cbed53760994f3d33b1edc7d5"},"schema_version":"1.0","source":{"id":"2312.03849","kind":"arxiv","version":2}},"canonical_sha256":"a3c2713284b1c649d16a2d125d084e1cde88fe7a4b0ec33012e3072a563856d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3c2713284b1c649d16a2d125d084e1cde88fe7a4b0ec33012e3072a563856d6","first_computed_at":"2026-07-05T07:59:20.170910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:20.170910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rxoEM7X3/9kFYW+f2aq4rFpRCuHa6P7I4uTLj3TcWELr0JJJ6siu7OHcwqLhI0M7TR0mfLtw+dVJf8D7EFaEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:20.171433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03849","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18a1e28928fc86fb2b2ee0eaba812f9d5b863b1030470445fd6f98a84fee402f","sha256:64a2b67fba29ed326ed057923960f78a4366ae9f29a133ae765a520794276966"],"state_sha256":"c98d6f32f631c08604a1f89a89c68a4043feb0558922f340cae2100e30d28e63"}