{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SDJY5J6SEHJ5HMM5TN4YBNLSWB","short_pith_number":"pith:SDJY5J6S","schema_version":"1.0","canonical_sha256":"90d38ea7d221d3d3b19d9b7980b572b04f2ec314319fe60bbf16ef3a288912c8","source":{"kind":"arxiv","id":"2411.04709","version":2},"attestation_state":"computed","paper":{"title":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenhao Wang, Yi Yang","submitted_at":"2024-11-05T18:52:43Z","abstract_excerpt":"Video generation models are revolutionizing content creation, with image-to-video models drawing increasing attention due to their enhanced controllability, visual consistency, and practical applications. However, despite their popularity, these models rely on user-provided text and image prompts, and there is currently no dedicated dataset for studying these prompts. In this paper, we introduce TIP-I2V, the first large-scale dataset of over 1.70 million unique user-provided Text and Image Prompts specifically for Image-to-Video generation. Additionally, we provide the corresponding generated "},"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":"2411.04709","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:52:43Z","cross_cats_sorted":[],"title_canon_sha256":"db24ec1b984a6a4fa88cc36da4fdafccd37b8d4d51aa5bf85fc4765353ca2d21","abstract_canon_sha256":"841491d6818b60372039237c4371ebbe09c17c95673bb568742fafd25974e237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:01.870684Z","signature_b64":"79On5k5/c9FDNLXnNqaJq0Tr04ezH+rnDJy69Rwg1lHSXksLA2efngLelgIsVVQv7TyiJ/Qp8D1fvDXpIFyeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90d38ea7d221d3d3b19d9b7980b572b04f2ec314319fe60bbf16ef3a288912c8","last_reissued_at":"2026-07-05T11:34:01.870259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:01.870259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenhao Wang, Yi Yang","submitted_at":"2024-11-05T18:52:43Z","abstract_excerpt":"Video generation models are revolutionizing content creation, with image-to-video models drawing increasing attention due to their enhanced controllability, visual consistency, and practical applications. However, despite their popularity, these models rely on user-provided text and image prompts, and there is currently no dedicated dataset for studying these prompts. In this paper, we introduce TIP-I2V, the first large-scale dataset of over 1.70 million unique user-provided Text and Image Prompts specifically for Image-to-Video generation. Additionally, we provide the corresponding generated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04709","kind":"arxiv","version":2},"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/2411.04709/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":"2411.04709","created_at":"2026-07-05T11:34:01.870327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04709v2","created_at":"2026-07-05T11:34:01.870327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04709","created_at":"2026-07-05T11:34:01.870327+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDJY5J6SEHJ5","created_at":"2026-07-05T11:34:01.870327+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDJY5J6SEHJ5HMM5","created_at":"2026-07-05T11:34:01.870327+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDJY5J6S","created_at":"2026-07-05T11:34:01.870327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10771","citing_title":"AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB","json":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB.json","graph_json":"https://pith.science/api/pith-number/SDJY5J6SEHJ5HMM5TN4YBNLSWB/graph.json","events_json":"https://pith.science/api/pith-number/SDJY5J6SEHJ5HMM5TN4YBNLSWB/events.json","paper":"https://pith.science/paper/SDJY5J6S"},"agent_actions":{"view_html":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB","download_json":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB.json","view_paper":"https://pith.science/paper/SDJY5J6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04709&json=true","fetch_graph":"https://pith.science/api/pith-number/SDJY5J6SEHJ5HMM5TN4YBNLSWB/graph.json","fetch_events":"https://pith.science/api/pith-number/SDJY5J6SEHJ5HMM5TN4YBNLSWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB/action/storage_attestation","attest_author":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB/action/author_attestation","sign_citation":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB/action/citation_signature","submit_replication":"https://pith.science/pith/SDJY5J6SEHJ5HMM5TN4YBNLSWB/action/replication_record"}},"created_at":"2026-07-05T11:34:01.870327+00:00","updated_at":"2026-07-05T11:34:01.870327+00:00"}