{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MEZFAPF7ZTOXFGQOGU4ZSSH43R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6827e18225b225bc3730dbf3d51479023ad5715d013d0c5f768228ca983c3566","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T00:21:24Z","title_canon_sha256":"0c641f19ca5461fd760c0c7519fe3b83f4ee2d1f034537bee30dc2a2988585a1"},"schema_version":"1.0","source":{"id":"2507.00334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00334","created_at":"2026-07-05T11:30:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00334v1","created_at":"2026-07-05T11:30:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00334","created_at":"2026-07-05T11:30:06Z"},{"alias_kind":"pith_short_12","alias_value":"MEZFAPF7ZTOX","created_at":"2026-07-05T11:30:06Z"},{"alias_kind":"pith_short_16","alias_value":"MEZFAPF7ZTOXFGQO","created_at":"2026-07-05T11:30:06Z"},{"alias_kind":"pith_short_8","alias_value":"MEZFAPF7","created_at":"2026-07-05T11:30:06Z"}],"graph_snapshots":[{"event_id":"sha256:903dc8bfb44a9ba4d890ce8fa6f9ab5a027727ba401285b305e16e4e79969605","target":"graph","created_at":"2026-07-05T11:30:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.00334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ching-Yao Chuang, Felix Juefei-Xu, Haoyu Ma, Mengyi Shan, Peizhao Zhang, Tingbo Hou, Zecheng He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T00:21:24Z","title":"Populate-A-Scene: Affordance-Aware Human Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00334","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4cca4c579292c28dcdb44a2bc21a814b8b8c4e3ee5ee050b810bbdaa02a67a72","target":"record","created_at":"2026-07-05T11:30:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6827e18225b225bc3730dbf3d51479023ad5715d013d0c5f768228ca983c3566","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T00:21:24Z","title_canon_sha256":"0c641f19ca5461fd760c0c7519fe3b83f4ee2d1f034537bee30dc2a2988585a1"},"schema_version":"1.0","source":{"id":"2507.00334","kind":"arxiv","version":1}},"canonical_sha256":"6132503cbfccdd729a0e35399948fcdc71df34f0ecec38fcde45198658544864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6132503cbfccdd729a0e35399948fcdc71df34f0ecec38fcde45198658544864","first_computed_at":"2026-07-05T11:30:06.443772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:06.443772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hXHBiAyWlxqvb5t/qLK3UWZYgkoGauy+jUwzpp38z3hgjJJjdZElqxXWDIvtc6IkgqntXQu+WGDEmHPwUisuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:06.444187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cca4c579292c28dcdb44a2bc21a814b8b8c4e3ee5ee050b810bbdaa02a67a72","sha256:903dc8bfb44a9ba4d890ce8fa6f9ab5a027727ba401285b305e16e4e79969605"],"state_sha256":"088b8c030c0114fa10bdedb0cb63c438f73878ec04535cbff9a01721f1c23089"}