{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GDU2EBDOCDPA6KNO2WZSZ6EAH2","short_pith_number":"pith:GDU2EBDO","canonical_record":{"source":{"id":"2412.09283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e70b88621b49a069434081cd328f0bb7dab726023a5a8e7b445dc231c6712865","abstract_canon_sha256":"87ac446d2df4904582020c6424d4e37e811ac8879596b5145522e8a62a6fadc0"},"schema_version":"1.0"},"canonical_sha256":"30e9a2046e10de0f29aed5b32cf8803eb0cadfbba7b916a709826783038f4b6b","source":{"kind":"arxiv","id":"2412.09283","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09283","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09283v1","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09283","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"GDU2EBDOCDPA","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"GDU2EBDOCDPA6KNO","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"GDU2EBDO","created_at":"2026-07-05T09:48:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GDU2EBDOCDPA6KNO2WZSZ6EAH2","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e70b88621b49a069434081cd328f0bb7dab726023a5a8e7b445dc231c6712865","abstract_canon_sha256":"87ac446d2df4904582020c6424d4e37e811ac8879596b5145522e8a62a6fadc0"},"schema_version":"1.0"},"canonical_sha256":"30e9a2046e10de0f29aed5b32cf8803eb0cadfbba7b916a709826783038f4b6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:22.619903Z","signature_b64":"3G+FnXg02RCD8dEhMQl4QK7bEv7Fzgum1RMFivXSwAHnoDqzW4Fpkmob/62E5wNVk81iYg89vGOmRxVEqzQCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e9a2046e10de0f29aed5b32cf8803eb0cadfbba7b916a709826783038f4b6b","last_reissued_at":"2026-07-05T09:48:22.619395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:22.619395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09283","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfsRBDbM6Ty6uIpU7+UI2zcbuvYbwqqj+8THv0cbs9ZkQIOh2Wb46H3TptLwQosGBTDr17HudsN/7Mf02fqgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:15:36.192841Z"},"content_sha256":"fb50709759ee30ccc27d8b6e77b53984ea4553536b52d7820608b18300396479","schema_version":"1.0","event_id":"sha256:fb50709759ee30ccc27d8b6e77b53984ea4553536b52d7820608b18300396479"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GDU2EBDOCDPA6KNO2WZSZ6EAH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Jian Yang, Kepan Nan, Penghao Zhou, Rui Xie, Tiehan Fan, Xiang Li, Ying Tai, Zhenheng Yang","submitted_at":"2024-12-12T13:48:40Z","abstract_excerpt":"Text-to-video generation has evolved rapidly in recent years, delivering remarkable results. Training typically relies on video-caption paired data, which plays a crucial role in enhancing generation performance. However, current video captions often suffer from insufficient details, hallucinations and imprecise motion depiction, affecting the fidelity and consistency of generated videos. In this work, we propose a novel instance-aware structured caption framework, termed InstanceCap, to achieve instance-level and fine-grained video caption for the first time. Based on this scheme, we design a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09283","kind":"arxiv","version":1},"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/2412.09283/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":"2026-07-05T09:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qaU/gDDAltK5SxkuNStcUgImBFVnQuWwvYVzwlizXUCXMDuQo7RyDom9KUjrfBNiZttgdTkQJh9OPzlszk5CBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:15:36.193740Z"},"content_sha256":"ed8683e7a38d2ee8a4387e00896d4cf89caf70aae0b1ace001306d8a9f91f679","schema_version":"1.0","event_id":"sha256:ed8683e7a38d2ee8a4387e00896d4cf89caf70aae0b1ace001306d8a9f91f679"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2/bundle.json","state_url":"https://pith.science/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2/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":"2026-08-18T12:15:36Z","links":{"resolver":"https://pith.science/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2","bundle":"https://pith.science/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2/bundle.json","state":"https://pith.science/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDU2EBDOCDPA6KNO2WZSZ6EAH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GDU2EBDOCDPA6KNO2WZSZ6EAH2","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":"87ac446d2df4904582020c6424d4e37e811ac8879596b5145522e8a62a6fadc0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:48:40Z","title_canon_sha256":"e70b88621b49a069434081cd328f0bb7dab726023a5a8e7b445dc231c6712865"},"schema_version":"1.0","source":{"id":"2412.09283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09283","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09283v1","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09283","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"GDU2EBDOCDPA","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"GDU2EBDOCDPA6KNO","created_at":"2026-07-05T09:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"GDU2EBDO","created_at":"2026-07-05T09:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:ed8683e7a38d2ee8a4387e00896d4cf89caf70aae0b1ace001306d8a9f91f679","target":"graph","created_at":"2026-07-05T09:48:22Z","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/2412.09283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video generation has evolved rapidly in recent years, delivering remarkable results. Training typically relies on video-caption paired data, which plays a crucial role in enhancing generation performance. However, current video captions often suffer from insufficient details, hallucinations and imprecise motion depiction, affecting the fidelity and consistency of generated videos. In this work, we propose a novel instance-aware structured caption framework, termed InstanceCap, to achieve instance-level and fine-grained video caption for the first time. Based on this scheme, we design a","authors_text":"Chaoyou Fu, Jian Yang, Kepan Nan, Penghao Zhou, Rui Xie, Tiehan Fan, Xiang Li, Ying Tai, Zhenheng Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:48:40Z","title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09283","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:fb50709759ee30ccc27d8b6e77b53984ea4553536b52d7820608b18300396479","target":"record","created_at":"2026-07-05T09:48:22Z","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":"87ac446d2df4904582020c6424d4e37e811ac8879596b5145522e8a62a6fadc0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:48:40Z","title_canon_sha256":"e70b88621b49a069434081cd328f0bb7dab726023a5a8e7b445dc231c6712865"},"schema_version":"1.0","source":{"id":"2412.09283","kind":"arxiv","version":1}},"canonical_sha256":"30e9a2046e10de0f29aed5b32cf8803eb0cadfbba7b916a709826783038f4b6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30e9a2046e10de0f29aed5b32cf8803eb0cadfbba7b916a709826783038f4b6b","first_computed_at":"2026-07-05T09:48:22.619395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:22.619395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3G+FnXg02RCD8dEhMQl4QK7bEv7Fzgum1RMFivXSwAHnoDqzW4Fpkmob/62E5wNVk81iYg89vGOmRxVEqzQCAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:22.619903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb50709759ee30ccc27d8b6e77b53984ea4553536b52d7820608b18300396479","sha256:ed8683e7a38d2ee8a4387e00896d4cf89caf70aae0b1ace001306d8a9f91f679"],"state_sha256":"889de815c7ab6b9618baee02eed174bb383ef8d5d288637834ee18888b08ad60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6j9OfweNIEVBL4tGEh6vOpVXttJKxAYsaNYn216WpvzMGsKcfF1zeXAgDJ4qMhGPoH6vgaO9DYF0lT9wLguYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:15:36.206998Z","bundle_sha256":"e41c5acd8f71d2dd9a8df0794d2330de6ee72a5b5265026a5977276f3bc65035"}}