{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7JCTBYUQ6AM23OYMEN4XMYLDOT","short_pith_number":"pith:7JCTBYUQ","schema_version":"1.0","canonical_sha256":"fa4530e290f019adbb0c237976616374d52bd1f6fc8be81d41602d893b2d0abc","source":{"kind":"arxiv","id":"2406.14477","version":1},"attestation_state":"computed","paper":{"title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CV","authors_text":"Jiaming Ji, Josef Dai, Taiye Chen, Tianle Chen, Xuyao Wang, Yaodong Yang, Ziran Yang","submitted_at":"2024-06-20T16:38:56Z","abstract_excerpt":"To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values. This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness. To capture in-depth human preferences and facilitate structured reasoning by crowdworkers, we subdivide helpfulness into 4 sub-dimensions and harmlessness into 12 sub-categories, serving as the basis for pilot annotations. The SafeSora dataset includes 14,711 unique prompts, 57,3"},"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":"2406.14477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T16:38:56Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"d65184e21f25ed006d1bb6f904781ffa9123da8854a37f980688c0ea8a5e2864","abstract_canon_sha256":"9e472b1413a403cf7a60bcb5b71b8c395e84b41101ad6a78b84cd28b86f2a0ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:51.271881Z","signature_b64":"aQ78HzyVp5GSCZBgXsWxWOKLjrlIEPfEXIwL6CNMVlJZH2U+k9ud+UxdW5/e5xNTANRKgCQpP2fNEOV72kgrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa4530e290f019adbb0c237976616374d52bd1f6fc8be81d41602d893b2d0abc","last_reissued_at":"2026-07-05T08:34:51.271437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:51.271437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CV","authors_text":"Jiaming Ji, Josef Dai, Taiye Chen, Tianle Chen, Xuyao Wang, Yaodong Yang, Ziran Yang","submitted_at":"2024-06-20T16:38:56Z","abstract_excerpt":"To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values. This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness. To capture in-depth human preferences and facilitate structured reasoning by crowdworkers, we subdivide helpfulness into 4 sub-dimensions and harmlessness into 12 sub-categories, serving as the basis for pilot annotations. The SafeSora dataset includes 14,711 unique prompts, 57,3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14477","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/2406.14477/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":"2406.14477","created_at":"2026-07-05T08:34:51.271490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14477v1","created_at":"2026-07-05T08:34:51.271490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14477","created_at":"2026-07-05T08:34:51.271490+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JCTBYUQ6AM2","created_at":"2026-07-05T08:34:51.271490+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JCTBYUQ6AM23OYM","created_at":"2026-07-05T08:34:51.271490+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JCTBYUQ","created_at":"2026-07-05T08:34:51.271490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01481","citing_title":"SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT","json":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT.json","graph_json":"https://pith.science/api/pith-number/7JCTBYUQ6AM23OYMEN4XMYLDOT/graph.json","events_json":"https://pith.science/api/pith-number/7JCTBYUQ6AM23OYMEN4XMYLDOT/events.json","paper":"https://pith.science/paper/7JCTBYUQ"},"agent_actions":{"view_html":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT","download_json":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT.json","view_paper":"https://pith.science/paper/7JCTBYUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14477&json=true","fetch_graph":"https://pith.science/api/pith-number/7JCTBYUQ6AM23OYMEN4XMYLDOT/graph.json","fetch_events":"https://pith.science/api/pith-number/7JCTBYUQ6AM23OYMEN4XMYLDOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT/action/storage_attestation","attest_author":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT/action/author_attestation","sign_citation":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT/action/citation_signature","submit_replication":"https://pith.science/pith/7JCTBYUQ6AM23OYMEN4XMYLDOT/action/replication_record"}},"created_at":"2026-07-05T08:34:51.271490+00:00","updated_at":"2026-07-05T08:34:51.271490+00:00"}