{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KQJZTJYDRFBJJD4JDNB72H47OY","short_pith_number":"pith:KQJZTJYD","schema_version":"1.0","canonical_sha256":"541399a7038942948f891b43fd1f9f760af3a3170bdedd53901bde2fc9088569","source":{"kind":"arxiv","id":"2406.08656","version":1},"attestation_state":"computed","paper":{"title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiachen Li, Michael Saxon, Tsu-Jui Fu, Weixi Feng, Wenhu Chen, William Yang Wang","submitted_at":"2024-06-12T21:41:32Z","abstract_excerpt":"Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move beyond evaluating simple actions and argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.08656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T21:41:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"27182f13a84db41a9b1f00fd67c1c266d2d64ef91612136469da67b2dcdd1ca8","abstract_canon_sha256":"00cc1034ed730bb6135549b9af3d017063815ee0cabf2988aa0b3ff33e131ca8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:20.839626Z","signature_b64":"c43vWNooOJq/tlF23jHMBw6I9cY2rYvQsLkBPhc5J7UKlpUzZvAh/iDAaN0GNc+pdWkgDC8m1n6dB4UUDGUkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"541399a7038942948f891b43fd1f9f760af3a3170bdedd53901bde2fc9088569","last_reissued_at":"2026-07-05T08:31:20.839027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:20.839027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiachen Li, Michael Saxon, Tsu-Jui Fu, Weixi Feng, Wenhu Chen, William Yang Wang","submitted_at":"2024-06-12T21:41:32Z","abstract_excerpt":"Video generation has many unique challenges beyond those of image generation. The temporal dimension introduces extensive possible variations across frames, over which consistency and continuity may be violated. In this study, we move beyond evaluating simple actions and argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08656","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/2406.08656/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.08656","created_at":"2026-07-05T08:31:20.839107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08656v1","created_at":"2026-07-05T08:31:20.839107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08656","created_at":"2026-07-05T08:31:20.839107+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQJZTJYDRFBJ","created_at":"2026-07-05T08:31:20.839107+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQJZTJYDRFBJJD4J","created_at":"2026-07-05T08:31:20.839107+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQJZTJYD","created_at":"2026-07-05T08:31:20.839107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20545","citing_title":"Current World Models Lack a Persistent State Core","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10620","citing_title":"Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26244","citing_title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23699","citing_title":"CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17180","citing_title":"We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19092","citing_title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19092","citing_title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY","json":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY.json","graph_json":"https://pith.science/api/pith-number/KQJZTJYDRFBJJD4JDNB72H47OY/graph.json","events_json":"https://pith.science/api/pith-number/KQJZTJYDRFBJJD4JDNB72H47OY/events.json","paper":"https://pith.science/paper/KQJZTJYD"},"agent_actions":{"view_html":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY","download_json":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY.json","view_paper":"https://pith.science/paper/KQJZTJYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08656&json=true","fetch_graph":"https://pith.science/api/pith-number/KQJZTJYDRFBJJD4JDNB72H47OY/graph.json","fetch_events":"https://pith.science/api/pith-number/KQJZTJYDRFBJJD4JDNB72H47OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY/action/storage_attestation","attest_author":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY/action/author_attestation","sign_citation":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY/action/citation_signature","submit_replication":"https://pith.science/pith/KQJZTJYDRFBJJD4JDNB72H47OY/action/replication_record"}},"created_at":"2026-07-05T08:31:20.839107+00:00","updated_at":"2026-07-05T08:31:20.839107+00:00"}