{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ONP3JE5OB2H37T3JAGY5IWT3VD","short_pith_number":"pith:ONP3JE5O","schema_version":"1.0","canonical_sha256":"735fb493ae0e8fbfcf6901b1d45a7ba8f730916da24b5835b88ca348528eb89d","source":{"kind":"arxiv","id":"2503.23715","version":1},"attestation_state":"computed","paper":{"title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Jie Li, Kun Liu, Qi Liu, Wu Liu, Xiaodong He, Xinchen Liu, Yongdong Zhang","submitted_at":"2025-03-31T04:30:34Z","abstract_excerpt":"Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI. To address this issue, we introduce HOIGen-1M, the first largescale dataset for HOI Generation, consisting of over one million high-quality videos collected from diverse sources. In particular, to guarantee the high quality of videos, we first design an efficient framework to automatically curate HOI videos using the powe"},"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":"2503.23715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T04:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"f9829b285384e276211d241b1833d99be5998b88e428667a2d937a86ac75a4b8","abstract_canon_sha256":"3bf1c8bc4d8a0da35c7e1c1ecb770c5a99480120a4d23d6f727c220eadcf20b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:58.380403Z","signature_b64":"i00WnsrNLE2lkzV31pMqyubSG+LnrUemv50un7qr5y7GeOtcPRO1we6lhRmMF73Tpj9Dvj/lJadl3URinQsXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"735fb493ae0e8fbfcf6901b1d45a7ba8f730916da24b5835b88ca348528eb89d","last_reissued_at":"2026-07-05T10:41:58.379968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:58.379968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Jie Li, Kun Liu, Qi Liu, Wu Liu, Xiaodong He, Xinchen Liu, Yongdong Zhang","submitted_at":"2025-03-31T04:30:34Z","abstract_excerpt":"Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI. To address this issue, we introduce HOIGen-1M, the first largescale dataset for HOI Generation, consisting of over one million high-quality videos collected from diverse sources. In particular, to guarantee the high quality of videos, we first design an efficient framework to automatically curate HOI videos using the powe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23715","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/2503.23715/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":"2503.23715","created_at":"2026-07-05T10:41:58.380029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23715v1","created_at":"2026-07-05T10:41:58.380029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23715","created_at":"2026-07-05T10:41:58.380029+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONP3JE5OB2H3","created_at":"2026-07-05T10:41:58.380029+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONP3JE5OB2H37T3J","created_at":"2026-07-05T10:41:58.380029+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONP3JE5O","created_at":"2026-07-05T10:41:58.380029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04549","citing_title":"MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD","json":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD.json","graph_json":"https://pith.science/api/pith-number/ONP3JE5OB2H37T3JAGY5IWT3VD/graph.json","events_json":"https://pith.science/api/pith-number/ONP3JE5OB2H37T3JAGY5IWT3VD/events.json","paper":"https://pith.science/paper/ONP3JE5O"},"agent_actions":{"view_html":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD","download_json":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD.json","view_paper":"https://pith.science/paper/ONP3JE5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23715&json=true","fetch_graph":"https://pith.science/api/pith-number/ONP3JE5OB2H37T3JAGY5IWT3VD/graph.json","fetch_events":"https://pith.science/api/pith-number/ONP3JE5OB2H37T3JAGY5IWT3VD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD/action/storage_attestation","attest_author":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD/action/author_attestation","sign_citation":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD/action/citation_signature","submit_replication":"https://pith.science/pith/ONP3JE5OB2H37T3JAGY5IWT3VD/action/replication_record"}},"created_at":"2026-07-05T10:41:58.380029+00:00","updated_at":"2026-07-05T10:41:58.380029+00:00"}