{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UPBHCMUEWHDETULKFUJF2CCODT","short_pith_number":"pith:UPBHCMUE","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"},"canonical_sha256":"a3c2713284b1c649d16a2d125d084e1cde88fe7a4b0ec33012e3072a563856d6","source":{"kind":"arxiv","id":"2312.03849","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UPBHCMUEWHDETULKFUJF2CCODT","target":"record","payload":{"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"},"canonical_sha256":"a3c2713284b1c649d16a2d125d084e1cde88fe7a4b0ec33012e3072a563856d6","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"},"source_kind":"arxiv","source_id":"2312.03849","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/8UV5kXg7SKSMsnQiE1MPDPiSEUK7YsE6Ugw4xQ94ZeA7KOclzElJWbh2Y1QmiP07eJ0m+2csMRTbrvDXJ4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:02:24.425091Z"},"content_sha256":"18a1e28928fc86fb2b2ee0eaba812f9d5b863b1030470445fd6f98a84fee402f","schema_version":"1.0","event_id":"sha256:18a1e28928fc86fb2b2ee0eaba812f9d5b863b1030470445fd6f98a84fee402f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UPBHCMUEWHDETULKFUJF2CCODT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Di0LFENhBv/dQMnsFePZpzBqONKASCdhDwCYKS+3EkXemglOx5tJzH+5/0KjcBSOlja+8XtwpM/gFqKVidImBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:02:24.425784Z"},"content_sha256":"64a2b67fba29ed326ed057923960f78a4366ae9f29a133ae765a520794276966","schema_version":"1.0","event_id":"sha256:64a2b67fba29ed326ed057923960f78a4366ae9f29a133ae765a520794276966"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/bundle.json","state_url":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPBHCMUEWHDETULKFUJF2CCODT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T19:02:24Z","links":{"resolver":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT","bundle":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/bundle.json","state":"https://pith.science/pith/UPBHCMUEWHDETULKFUJF2CCODT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPBHCMUEWHDETULKFUJF2CCODT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AkLkooqWNpoPpZTMMH/JPjnX22XnoVkKHtbF9XLMtd0yS7sfNnMmWl7AFI0ZVRQTmTqal6BCMR9JGEaJ8ZsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:02:24.434294Z","bundle_sha256":"d99f294207e7ef3c240613df65fa50ada8d51b752dfbbc3272022f6d2ff8757b"}}