{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KQJA7RN3JSG2K3ABSVCHARWIRZ","short_pith_number":"pith:KQJA7RN3","schema_version":"1.0","canonical_sha256":"54120fc5bb4c8da56c0195447046c88e59b3c159d593ad87839cdc2e823c23c9","source":{"kind":"arxiv","id":"2603.07514","version":3},"attestation_state":"computed","paper":{"title":"A Unified View of Score-Based and Drifting Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bac Nguyen, Chieh-Hsin Lai, Molei Tao, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2026-03-08T07:41:36Z","abstract_excerpt":"Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, thereby defining a transport direction for generated samples. In this paper, we show that drifting is more closely connected to score-based generative modeling than it may first appear, establishing a precise link to the score-matching principle "},"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":"2603.07514","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-08T07:41:36Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6bd3626ca40c42a9467e54f6c045880830fc54aac81ebbc4c2070f2bb22d5203","abstract_canon_sha256":"a4106050ce1af064a790a7fce8136ea34b04b2941b61ad61096cf65ef3f06848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:35.862732Z","signature_b64":"OGJ5hjG7cIZOu/V2C9pEpgtkgVnG4xroY9RwHhqszEuocWmbQjtc06QJQMXugl9e80tO+0PJlElyEo8io33HAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54120fc5bb4c8da56c0195447046c88e59b3c159d593ad87839cdc2e823c23c9","last_reissued_at":"2026-05-20T00:00:35.862044Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:35.862044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified View of Score-Based and Drifting Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bac Nguyen, Chieh-Hsin Lai, Molei Tao, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2026-03-08T07:41:36Z","abstract_excerpt":"Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, thereby defining a transport direction for generated samples. In this paper, we show that drifting is more closely connected to score-based generative modeling than it may first appear, establishing a precise link to the score-matching principle "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07514","kind":"arxiv","version":3},"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/2603.07514/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":"2603.07514","created_at":"2026-05-20T00:00:35.862167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07514v3","created_at":"2026-05-20T00:00:35.862167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07514","created_at":"2026-05-20T00:00:35.862167+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQJA7RN3JSG2","created_at":"2026-05-20T00:00:35.862167+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQJA7RN3JSG2K3AB","created_at":"2026-05-20T00:00:35.862167+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQJA7RN3","created_at":"2026-05-20T00:00:35.862167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.11755","citing_title":"One-Step Generative Modeling via Wasserstein Gradient Flows","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24196","citing_title":"Identifiability and Stability of Generative Drifting with Companion-Elliptic Kernel Families","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24196","citing_title":"Identifiability and Stability of Generative Drifting with Companion-Elliptic Kernel Families","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05118","citing_title":"On the Wasserstein Gradient Flow Interpretation of Drifting Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04060","citing_title":"Lookahead Drifting Model","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07327","citing_title":"Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07727","citing_title":"Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07319","citing_title":"Generative Modeling with Flux Matching","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ","json":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ.json","graph_json":"https://pith.science/api/pith-number/KQJA7RN3JSG2K3ABSVCHARWIRZ/graph.json","events_json":"https://pith.science/api/pith-number/KQJA7RN3JSG2K3ABSVCHARWIRZ/events.json","paper":"https://pith.science/paper/KQJA7RN3"},"agent_actions":{"view_html":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ","download_json":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ.json","view_paper":"https://pith.science/paper/KQJA7RN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07514&json=true","fetch_graph":"https://pith.science/api/pith-number/KQJA7RN3JSG2K3ABSVCHARWIRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KQJA7RN3JSG2K3ABSVCHARWIRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ/action/storage_attestation","attest_author":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ/action/author_attestation","sign_citation":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ/action/citation_signature","submit_replication":"https://pith.science/pith/KQJA7RN3JSG2K3ABSVCHARWIRZ/action/replication_record"}},"created_at":"2026-05-20T00:00:35.862167+00:00","updated_at":"2026-05-20T00:00:35.862167+00:00"}