{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KI7Y2PZTMU2EHB3MPFOXLSVTNI","short_pith_number":"pith:KI7Y2PZT","schema_version":"1.0","canonical_sha256":"523f8d3f33653443876c795d75cab36a29a2e6dfb0d10a6a7aac67466ac2aaf0","source":{"kind":"arxiv","id":"2506.14607","version":1},"attestation_state":"computed","paper":{"title":"Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"David I. Inouye, Jim Lim, Ziyu Gong","submitted_at":"2025-06-17T15:08:16Z","abstract_excerpt":"Distribution matching (DM) is a versatile domain-invariant representation learning technique that has been applied to tasks such as fair classification, domain adaptation, and domain translation. Non-parametric DM methods struggle with scalability and adversarial DM approaches suffer from instability and mode collapse. While likelihood-based methods are a promising alternative, they often impose unnecessary biases through fixed priors or require explicit density models (e.g., flows) that can be challenging to train. We address this limitation by introducing a novel approach to training likelih"},"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":"2506.14607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T15:08:16Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"ff2d89e88afa8909ff0a4623ea0b6c54c409e77b1182e95a0ecbe2a1cea00772","abstract_canon_sha256":"0af0ae5d4ac962bd399e746603f0def99ab054ff04934842df26189e74f7f538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:59.703612Z","signature_b64":"aMpD8oi+AChf6gRhNl0n1MWg1WKT+fUliQEuXnvPs6TCA2Z9bJ6AKcQJovZcD1NBG6m+1IYToskL2ugtaX+NDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"523f8d3f33653443876c795d75cab36a29a2e6dfb0d10a6a7aac67466ac2aaf0","last_reissued_at":"2026-07-05T11:22:59.703097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:59.703097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"David I. Inouye, Jim Lim, Ziyu Gong","submitted_at":"2025-06-17T15:08:16Z","abstract_excerpt":"Distribution matching (DM) is a versatile domain-invariant representation learning technique that has been applied to tasks such as fair classification, domain adaptation, and domain translation. Non-parametric DM methods struggle with scalability and adversarial DM approaches suffer from instability and mode collapse. While likelihood-based methods are a promising alternative, they often impose unnecessary biases through fixed priors or require explicit density models (e.g., flows) that can be challenging to train. We address this limitation by introducing a novel approach to training likelih"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14607","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/2506.14607/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":"2506.14607","created_at":"2026-07-05T11:22:59.703167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14607v1","created_at":"2026-07-05T11:22:59.703167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14607","created_at":"2026-07-05T11:22:59.703167+00:00"},{"alias_kind":"pith_short_12","alias_value":"KI7Y2PZTMU2E","created_at":"2026-07-05T11:22:59.703167+00:00"},{"alias_kind":"pith_short_16","alias_value":"KI7Y2PZTMU2EHB3M","created_at":"2026-07-05T11:22:59.703167+00:00"},{"alias_kind":"pith_short_8","alias_value":"KI7Y2PZT","created_at":"2026-07-05T11:22:59.703167+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/KI7Y2PZTMU2EHB3MPFOXLSVTNI","json":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI.json","graph_json":"https://pith.science/api/pith-number/KI7Y2PZTMU2EHB3MPFOXLSVTNI/graph.json","events_json":"https://pith.science/api/pith-number/KI7Y2PZTMU2EHB3MPFOXLSVTNI/events.json","paper":"https://pith.science/paper/KI7Y2PZT"},"agent_actions":{"view_html":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI","download_json":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI.json","view_paper":"https://pith.science/paper/KI7Y2PZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14607&json=true","fetch_graph":"https://pith.science/api/pith-number/KI7Y2PZTMU2EHB3MPFOXLSVTNI/graph.json","fetch_events":"https://pith.science/api/pith-number/KI7Y2PZTMU2EHB3MPFOXLSVTNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI/action/storage_attestation","attest_author":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI/action/author_attestation","sign_citation":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI/action/citation_signature","submit_replication":"https://pith.science/pith/KI7Y2PZTMU2EHB3MPFOXLSVTNI/action/replication_record"}},"created_at":"2026-07-05T11:22:59.703167+00:00","updated_at":"2026-07-05T11:22:59.703167+00:00"}