{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MEZFAPF7ZTOXFGQOGU4ZSSH43R","short_pith_number":"pith:MEZFAPF7","schema_version":"1.0","canonical_sha256":"6132503cbfccdd729a0e35399948fcdc71df34f0ecec38fcde45198658544864","source":{"kind":"arxiv","id":"2507.00334","version":1},"attestation_state":"computed","paper":{"title":"Populate-A-Scene: Affordance-Aware Human Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ching-Yao Chuang, Felix Juefei-Xu, Haoyu Ma, Mengyi Shan, Peizhao Zhang, Tingbo Hou, Zecheng He","submitted_at":"2025-07-01T00:21:24Z","abstract_excerpt":"Can a video generation model be repurposed as an interactive world simulator? We explore the affordance perception potential of text-to-video models by teaching them to predict human-environment interaction. Given a scene image and a prompt describing human actions, we fine-tune the model to insert a person into the scene, while ensuring coherent behavior, appearance, harmonization, and scene affordance. Unlike prior work, we infer human affordance for video generation (i.e., where to insert a person and how they should behave) from a single scene image, without explicit conditions like boundi"},"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":"2507.00334","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T00:21:24Z","cross_cats_sorted":[],"title_canon_sha256":"0c641f19ca5461fd760c0c7519fe3b83f4ee2d1f034537bee30dc2a2988585a1","abstract_canon_sha256":"6827e18225b225bc3730dbf3d51479023ad5715d013d0c5f768228ca983c3566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:06.444187Z","signature_b64":"hXHBiAyWlxqvb5t/qLK3UWZYgkoGauy+jUwzpp38z3hgjJJjdZElqxXWDIvtc6IkgqntXQu+WGDEmHPwUisuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6132503cbfccdd729a0e35399948fcdc71df34f0ecec38fcde45198658544864","last_reissued_at":"2026-07-05T11:30:06.443772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:06.443772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Populate-A-Scene: Affordance-Aware Human Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ching-Yao Chuang, Felix Juefei-Xu, Haoyu Ma, Mengyi Shan, Peizhao Zhang, Tingbo Hou, Zecheng He","submitted_at":"2025-07-01T00:21:24Z","abstract_excerpt":"Can a video generation model be repurposed as an interactive world simulator? We explore the affordance perception potential of text-to-video models by teaching them to predict human-environment interaction. Given a scene image and a prompt describing human actions, we fine-tune the model to insert a person into the scene, while ensuring coherent behavior, appearance, harmonization, and scene affordance. Unlike prior work, we infer human affordance for video generation (i.e., where to insert a person and how they should behave) from a single scene image, without explicit conditions like boundi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00334","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/2507.00334/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":"2507.00334","created_at":"2026-07-05T11:30:06.443840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00334v1","created_at":"2026-07-05T11:30:06.443840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00334","created_at":"2026-07-05T11:30:06.443840+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEZFAPF7ZTOX","created_at":"2026-07-05T11:30:06.443840+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEZFAPF7ZTOXFGQO","created_at":"2026-07-05T11:30:06.443840+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEZFAPF7","created_at":"2026-07-05T11:30:06.443840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R","json":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R.json","graph_json":"https://pith.science/api/pith-number/MEZFAPF7ZTOXFGQOGU4ZSSH43R/graph.json","events_json":"https://pith.science/api/pith-number/MEZFAPF7ZTOXFGQOGU4ZSSH43R/events.json","paper":"https://pith.science/paper/MEZFAPF7"},"agent_actions":{"view_html":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R","download_json":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R.json","view_paper":"https://pith.science/paper/MEZFAPF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00334&json=true","fetch_graph":"https://pith.science/api/pith-number/MEZFAPF7ZTOXFGQOGU4ZSSH43R/graph.json","fetch_events":"https://pith.science/api/pith-number/MEZFAPF7ZTOXFGQOGU4ZSSH43R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R/action/storage_attestation","attest_author":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R/action/author_attestation","sign_citation":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R/action/citation_signature","submit_replication":"https://pith.science/pith/MEZFAPF7ZTOXFGQOGU4ZSSH43R/action/replication_record"}},"created_at":"2026-07-05T11:30:06.443840+00:00","updated_at":"2026-07-05T11:30:06.443840+00:00"}