{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CII2GZK2SZP77KCZU7JIYDSAMT","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":"4373cd70c934fc1ef9a1d51122a269f81162eb76b42a348e57a2b150945cf275","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T15:59:45Z","title_canon_sha256":"527c4de10b9b57936b3ab181015c3d39986afb77982cc2cc953422a06d47f34c"},"schema_version":"1.0","source":{"id":"1804.03608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03608","created_at":"2026-05-18T00:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03608v1","created_at":"2026-05-18T00:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03608","created_at":"2026-05-18T00:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"CII2GZK2SZP7","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CII2GZK2SZP77KCZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CII2GZK2","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:df87012eb750641528be98d1654a6b23099bd48b89376011452ee7a1093ab5d6","target":"graph","created_at":"2026-05-18T00:18:47Z","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"},"paper":{"abstract_excerpt":"Imagining a scene described in natural language with realistic layout and appearance of entities is the ultimate test of spatial, visual, and semantic world knowledge. Towards this goal, we present the Composition, Retrieval, and Fusion Network (CRAFT), a model capable of learning this knowledge from video-caption data and applying it while generating videos from novel captions. CRAFT explicitly predicts a temporal-layout of mentioned entities (characters and objects), retrieves spatio-temporal entity segments from a video database and fuses them to generate scene videos. Our contributions inc","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Derek Hoiem, Dustin Schwenk, Tanmay Gupta","cross_cats":["cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T15:59:45Z","title":"Imagine This! Scripts to Compositions to Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03608","kind":"arxiv","version":1},"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:a2f117c848a64e10da40e4ae7afef50f99f6a9afa3407bd0d5a8c9a0d319dde6","target":"record","created_at":"2026-05-18T00:18:47Z","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":"4373cd70c934fc1ef9a1d51122a269f81162eb76b42a348e57a2b150945cf275","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-10T15:59:45Z","title_canon_sha256":"527c4de10b9b57936b3ab181015c3d39986afb77982cc2cc953422a06d47f34c"},"schema_version":"1.0","source":{"id":"1804.03608","kind":"arxiv","version":1}},"canonical_sha256":"1211a3655a965fffa859a7d28c0e4064c7c84d3ae52b73d32dc98fa384ab2dbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1211a3655a965fffa859a7d28c0e4064c7c84d3ae52b73d32dc98fa384ab2dbf","first_computed_at":"2026-05-18T00:18:47.573785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:47.573785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lxiwp3T1qi9DF90oR4f/wEEnkAr84WuntqETPmFFABRYBqdM1tkmui+6Av9NCzw4hlKXv88D4bjEWU5+8uvWCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:47.574435Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.03608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2f117c848a64e10da40e4ae7afef50f99f6a9afa3407bd0d5a8c9a0d319dde6","sha256:df87012eb750641528be98d1654a6b23099bd48b89376011452ee7a1093ab5d6"],"state_sha256":"21fb0e4f892cf0a35f1ec767461ebb4a0cd5b7545670017903e49c734da9bd11"}