{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2LSMNSTJ6AYPERLC45QGW6WLAL","short_pith_number":"pith:2LSMNSTJ","schema_version":"1.0","canonical_sha256":"d2e4c6ca69f030f24562e7606b7acb02d2ec148a773f9a2a59b9c7f6a2119825","source":{"kind":"arxiv","id":"2505.21780","version":4},"attestation_state":"computed","paper":{"title":"Compositional Scene Understanding through Inverse Generative Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Justin Dauwels, Yanbo Wang, Yilun Du","submitted_at":"2025-05-27T21:25:11Z","abstract_excerpt":"Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to understand the properties of a scene given a natural image. We formulate scene understanding as an inverse generative modeling problem, where we seek to find conditional parameters of a visual generative model to best fit a given natural image. To enable this procedure to infer scene structure from images substantially different than those seen during training, we further propose"},"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":"2505.21780","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T21:25:11Z","cross_cats_sorted":[],"title_canon_sha256":"469cec2cf7aceef41eee2894cec8c29c8690a2835dd85b37ee35e340a012ecfb","abstract_canon_sha256":"383ac9a17b59b73475d667571d4d2309f7584054141e64c2d2b68723640dc5aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:04.923580Z","signature_b64":"5xGC5/CQcshTsG/cba9FMi9XkebsVKSzkjsc322MCF4XDkCQyjQyYnhzWhrQ58DSVGBVrmaA1z0msEM0PSpFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e4c6ca69f030f24562e7606b7acb02d2ec148a773f9a2a59b9c7f6a2119825","last_reissued_at":"2026-07-05T11:26:04.923149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:04.923149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Scene Understanding through Inverse Generative Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Justin Dauwels, Yanbo Wang, Yilun Du","submitted_at":"2025-05-27T21:25:11Z","abstract_excerpt":"Generative models have demonstrated remarkable abilities in generating high-fidelity visual content. In this work, we explore how generative models can further be used not only to synthesize visual content but also to understand the properties of a scene given a natural image. We formulate scene understanding as an inverse generative modeling problem, where we seek to find conditional parameters of a visual generative model to best fit a given natural image. To enable this procedure to infer scene structure from images substantially different than those seen during training, we further propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21780","kind":"arxiv","version":4},"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/2505.21780/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":"2505.21780","created_at":"2026-07-05T11:26:04.923211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21780v4","created_at":"2026-07-05T11:26:04.923211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21780","created_at":"2026-07-05T11:26:04.923211+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LSMNSTJ6AYP","created_at":"2026-07-05T11:26:04.923211+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LSMNSTJ6AYPERLC","created_at":"2026-07-05T11:26:04.923211+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LSMNSTJ","created_at":"2026-07-05T11:26:04.923211+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/2LSMNSTJ6AYPERLC45QGW6WLAL","json":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL.json","graph_json":"https://pith.science/api/pith-number/2LSMNSTJ6AYPERLC45QGW6WLAL/graph.json","events_json":"https://pith.science/api/pith-number/2LSMNSTJ6AYPERLC45QGW6WLAL/events.json","paper":"https://pith.science/paper/2LSMNSTJ"},"agent_actions":{"view_html":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL","download_json":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL.json","view_paper":"https://pith.science/paper/2LSMNSTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21780&json=true","fetch_graph":"https://pith.science/api/pith-number/2LSMNSTJ6AYPERLC45QGW6WLAL/graph.json","fetch_events":"https://pith.science/api/pith-number/2LSMNSTJ6AYPERLC45QGW6WLAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL/action/storage_attestation","attest_author":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL/action/author_attestation","sign_citation":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL/action/citation_signature","submit_replication":"https://pith.science/pith/2LSMNSTJ6AYPERLC45QGW6WLAL/action/replication_record"}},"created_at":"2026-07-05T11:26:04.923211+00:00","updated_at":"2026-07-05T11:26:04.923211+00:00"}