{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WNFYFV6OWAO7ILOHLJT6N54B6U","short_pith_number":"pith:WNFYFV6O","schema_version":"1.0","canonical_sha256":"b34b82d7ceb01df42dc75a67e6f781f505d23a29c2ba443e3964acb6f0396e60","source":{"kind":"arxiv","id":"2206.09021","version":1},"attestation_state":"computed","paper":{"title":"Conditional Permutation Invariant Flows","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam \\'Scibior, Berend Zwartsenberg, Frank Wood, Jonathan Wilder Lavington, Justice Sefas, Matthew Niedoba, Setareh Dabiri, Trevor Campbell, Vasileios Lioutas, Yunpeng Liu","submitted_at":"2022-06-17T21:43:38Z","abstract_excerpt":"We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density. This model is a continuous normalizing flow governed by permutation equivariant dynamics. These dynamics are driven by a learnable per-set-element term and pairwise interactions, both parametrized by deep neural networks. We illustrate the utility of this model via applications including (1) complex traffic scene generation conditioned on visually specified map information, and (2) object bounding box generation conditioned directly on images. We train our model by maximizing the exp"},"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":"2206.09021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-17T21:43:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"57297caf44ccb82ca13b92a1b5929b1269100a19eb28573d674a0aea93835e28","abstract_canon_sha256":"0962761edf1494830481be8beff3c585906fb001b0ff031ab6b34cdd217f5056"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:02.933997Z","signature_b64":"nbdbT8Tz3abw4zglhIQD/yRm+j30vDUWCwMg+uDF47jzM2qfBPH3rVawi2mPIkFX4d5u4C4wDCCP1pEQTw87Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b34b82d7ceb01df42dc75a67e6f781f505d23a29c2ba443e3964acb6f0396e60","last_reissued_at":"2026-07-05T04:33:02.933501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:02.933501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Permutation Invariant Flows","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam \\'Scibior, Berend Zwartsenberg, Frank Wood, Jonathan Wilder Lavington, Justice Sefas, Matthew Niedoba, Setareh Dabiri, Trevor Campbell, Vasileios Lioutas, Yunpeng Liu","submitted_at":"2022-06-17T21:43:38Z","abstract_excerpt":"We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density. This model is a continuous normalizing flow governed by permutation equivariant dynamics. These dynamics are driven by a learnable per-set-element term and pairwise interactions, both parametrized by deep neural networks. We illustrate the utility of this model via applications including (1) complex traffic scene generation conditioned on visually specified map information, and (2) object bounding box generation conditioned directly on images. We train our model by maximizing the exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09021","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/2206.09021/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":"2206.09021","created_at":"2026-07-05T04:33:02.933560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09021v1","created_at":"2026-07-05T04:33:02.933560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09021","created_at":"2026-07-05T04:33:02.933560+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNFYFV6OWAO7","created_at":"2026-07-05T04:33:02.933560+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNFYFV6OWAO7ILOH","created_at":"2026-07-05T04:33:02.933560+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNFYFV6O","created_at":"2026-07-05T04:33:02.933560+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/WNFYFV6OWAO7ILOHLJT6N54B6U","json":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U.json","graph_json":"https://pith.science/api/pith-number/WNFYFV6OWAO7ILOHLJT6N54B6U/graph.json","events_json":"https://pith.science/api/pith-number/WNFYFV6OWAO7ILOHLJT6N54B6U/events.json","paper":"https://pith.science/paper/WNFYFV6O"},"agent_actions":{"view_html":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U","download_json":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U.json","view_paper":"https://pith.science/paper/WNFYFV6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09021&json=true","fetch_graph":"https://pith.science/api/pith-number/WNFYFV6OWAO7ILOHLJT6N54B6U/graph.json","fetch_events":"https://pith.science/api/pith-number/WNFYFV6OWAO7ILOHLJT6N54B6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U/action/storage_attestation","attest_author":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U/action/author_attestation","sign_citation":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U/action/citation_signature","submit_replication":"https://pith.science/pith/WNFYFV6OWAO7ILOHLJT6N54B6U/action/replication_record"}},"created_at":"2026-07-05T04:33:02.933560+00:00","updated_at":"2026-07-05T04:33:02.933560+00:00"}