{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XMYYPLYY45Z5DE3C4RETHNGQFK","short_pith_number":"pith:XMYYPLYY","canonical_record":{"source":{"id":"2405.04682","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T21:52:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a68cb8f7b77254dfbefe0056c1aba4b50a092bc30daa8b7e3f1b74bf827323e3","abstract_canon_sha256":"0f9063a36b38e48e434f8407470b63ec2fb3538ac48b5cffefb0cf88de4358f4"},"schema_version":"1.0"},"canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","source":{"kind":"arxiv","id":"2405.04682","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04682","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04682v4","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04682","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"XMYYPLYY45Z5","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"XMYYPLYY45Z5DE3C","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"XMYYPLYY","created_at":"2026-07-05T09:32:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XMYYPLYY45Z5DE3C4RETHNGQFK","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04682","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T21:52:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a68cb8f7b77254dfbefe0056c1aba4b50a092bc30daa8b7e3f1b74bf827323e3","abstract_canon_sha256":"0f9063a36b38e48e434f8407470b63ec2fb3538ac48b5cffefb0cf88de4358f4"},"schema_version":"1.0"},"canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:44.011731Z","signature_b64":"WeS2hFiEwpmmHbASqUFQefyk/EjqSpqN17BV6z7ifFbG0fVOcCnLGm/TDsAv3gwLuQlF+nx9Kc6LjZ6w6DTBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","last_reissued_at":"2026-07-05T09:32:44.011213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:44.011213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04682","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yp353aVsWyjQdl7cWCxW5/tGvmzXzIegxJN8Xbwmaz0q4C3HGa4Y0NQOEF9g1lUJTokdBGEcCycx8kqLrSrVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:28:37.498004Z"},"content_sha256":"72e3e5bd16b7177fadf54ef0199e7539a959e4169f065bed07adc31827f4168a","schema_version":"1.0","event_id":"sha256:72e3e5bd16b7177fadf54ef0199e7539a959e4169f065bed07adc31827f4168a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XMYYPLYY45Z5DE3C4RETHNGQFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Hritik Bansal, Idan Szpektor, Kai-Wei Chang, Michal Yarom, Yonatan Bitton","submitted_at":"2024-05-07T21:52:39Z","abstract_excerpt":"Most of these text-to-video (T2V) generative models often produce single-scene video clips that depict an entity performing a particular action (e.g., 'a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., 'a red panda climbing a tree' followed by 'the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce a simple and effective Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04682","kind":"arxiv","version":4},"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/2405.04682/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":"2026-07-05T09:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L2bxOCEUntewNhrkTy0IMk7Kqe6HqqyIPLTid4ryq06YPSXV9HaKCAroxCctLkpKRDES5jrH57HKUNigmrveAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:28:37.498382Z"},"content_sha256":"54272c42d254755128bf1a8a697c6f5cac16a88d0328e9b70c0b057bfce8ab95","schema_version":"1.0","event_id":"sha256:54272c42d254755128bf1a8a697c6f5cac16a88d0328e9b70c0b057bfce8ab95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/bundle.json","state_url":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/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":"2026-07-07T11:28:37Z","links":{"resolver":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK","bundle":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/bundle.json","state":"https://pith.science/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMYYPLYY45Z5DE3C4RETHNGQFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XMYYPLYY45Z5DE3C4RETHNGQFK","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":"0f9063a36b38e48e434f8407470b63ec2fb3538ac48b5cffefb0cf88de4358f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T21:52:39Z","title_canon_sha256":"a68cb8f7b77254dfbefe0056c1aba4b50a092bc30daa8b7e3f1b74bf827323e3"},"schema_version":"1.0","source":{"id":"2405.04682","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04682","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04682v4","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04682","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"XMYYPLYY45Z5","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"XMYYPLYY45Z5DE3C","created_at":"2026-07-05T09:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"XMYYPLYY","created_at":"2026-07-05T09:32:44Z"}],"graph_snapshots":[{"event_id":"sha256:54272c42d254755128bf1a8a697c6f5cac16a88d0328e9b70c0b057bfce8ab95","target":"graph","created_at":"2026-07-05T09:32:44Z","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/2405.04682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most of these text-to-video (T2V) generative models often produce single-scene video clips that depict an entity performing a particular action (e.g., 'a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., 'a red panda climbing a tree' followed by 'the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce a simple and effective Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture t","authors_text":"Aditya Grover, Hritik Bansal, Idan Szpektor, Kai-Wei Chang, Michal Yarom, Yonatan Bitton","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T21:52:39Z","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04682","kind":"arxiv","version":4},"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":"sha256:72e3e5bd16b7177fadf54ef0199e7539a959e4169f065bed07adc31827f4168a","target":"record","created_at":"2026-07-05T09:32:44Z","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":"0f9063a36b38e48e434f8407470b63ec2fb3538ac48b5cffefb0cf88de4358f4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T21:52:39Z","title_canon_sha256":"a68cb8f7b77254dfbefe0056c1aba4b50a092bc30daa8b7e3f1b74bf827323e3"},"schema_version":"1.0","source":{"id":"2405.04682","kind":"arxiv","version":4}},"canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb3187af18e773d19362e44933b4d02ab53960b7afea74ccef95d7325cb860c4","first_computed_at":"2026-07-05T09:32:44.011213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:44.011213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WeS2hFiEwpmmHbASqUFQefyk/EjqSpqN17BV6z7ifFbG0fVOcCnLGm/TDsAv3gwLuQlF+nx9Kc6LjZ6w6DTBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:44.011731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04682","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72e3e5bd16b7177fadf54ef0199e7539a959e4169f065bed07adc31827f4168a","sha256:54272c42d254755128bf1a8a697c6f5cac16a88d0328e9b70c0b057bfce8ab95"],"state_sha256":"f566e995131ba145cbecf43d36697243a5b32ea377cca8a93d5a9bcc408a7059"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bzw88pbVRqsWMHadlZJKBME/dgwCg5Wrt1+ZuyWZ/UOAeJFh9ZcmwVxXCOwhFfZb8ApBBJ51LMQreu7pduonAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:28:37.500165Z","bundle_sha256":"6d5af4bfaa91d993d18a7d1be16c60cbce88fdf002bbb03a0e906380aa5770ac"}}