{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YN7ONYIEL7YZZO75TTX6JFRLOG","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":"19952b43dbc1c151c6ca3e29810617e24070ed79c9a0d6ea330c595bfef2fe82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T14:37:36Z","title_canon_sha256":"c63270aeec5c34a411a37ca8cd16dbfec36fb46c94e26a846bb5f19e4f89fa4f"},"schema_version":"1.0","source":{"id":"2312.07322","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07322","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07322v2","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07322","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"YN7ONYIEL7YZ","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"YN7ONYIEL7YZZO75","created_at":"2026-07-05T08:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"YN7ONYIE","created_at":"2026-07-05T08:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:f04cec602d1f30d3c52a20130d70bcdf8b5877599ddf02592a5fa39312e443e9","target":"graph","created_at":"2026-07-05T08:03:28Z","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/2312.07322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the task of generating temporally consistent and physically plausible images of actions and object state transformations. Given an input image and a text prompt describing the targeted transformation, our generated images preserve the environment and transform objects in the initial image. Our contributions are threefold. First, we leverage a large body of instructional videos and automatically mine a dataset of triplets of consecutive frames corresponding to initial object states, actions, and resulting object transformations. Second, equipped with this data, we develop and train a","authors_text":"Dima Damen, Ivan Laptev, Josef Sivic, Michael Wray, Tom\\'a\\v{s} Sou\\v{c}ek","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T14:37:36Z","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07322","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":"sha256:117bfff639bb7561efa56d395d8e9c12c61f73a4f79c86101a2220ffc36faf91","target":"record","created_at":"2026-07-05T08:03:28Z","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":"19952b43dbc1c151c6ca3e29810617e24070ed79c9a0d6ea330c595bfef2fe82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T14:37:36Z","title_canon_sha256":"c63270aeec5c34a411a37ca8cd16dbfec36fb46c94e26a846bb5f19e4f89fa4f"},"schema_version":"1.0","source":{"id":"2312.07322","kind":"arxiv","version":2}},"canonical_sha256":"c37ee6e1045ff19cbbfd9cefe4962b718513a93dcc842df4b883e37c6f30fe79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c37ee6e1045ff19cbbfd9cefe4962b718513a93dcc842df4b883e37c6f30fe79","first_computed_at":"2026-07-05T08:03:28.863509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:28.863509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SgEpndr3cJFiVoa3XmVptyVpCgmVaXvF9aRl9j1mktVarD8X7Cfc4FaBPXH9RNLXIk6u+hResV6QcM892SFRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:28.863981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07322","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:117bfff639bb7561efa56d395d8e9c12c61f73a4f79c86101a2220ffc36faf91","sha256:f04cec602d1f30d3c52a20130d70bcdf8b5877599ddf02592a5fa39312e443e9"],"state_sha256":"1150273a89c08b4d438f25c98e683cf3513ba036434913f0693995e880e8c559"}