{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JPOPWQLOEA2RVU43NNQ7BVJIDW","short_pith_number":"pith:JPOPWQLO","schema_version":"1.0","canonical_sha256":"4bdcfb416e20351ad39b6b61f0d5281d89ed7e143fda7a1cda0c223104f06621","source":{"kind":"arxiv","id":"2203.14206","version":1},"attestation_state":"computed","paper":{"title":"Denoising Likelihood Score Matching for Conditional Score-based Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo-Wun Cheng, Chen-Hao Chao, Chia-Che Chang, Chia-Ping Chen, Chun-Yi Lee, Wei-Fang Sun, Yi-Chen Lo, Yu-Lin Chang, Yu-Lun Liu","submitted_at":"2022-03-27T04:37:54Z","abstract_excerpt":"Many existing conditional score-based data generation methods utilize Bayes' theorem to decompose the gradients of a log posterior density into a mixture of scores. These methods facilitate the training procedure of conditional score models, as a mixture of scores can be separately estimated using a score model and a classifier. However, our analysis indicates that the training objectives for the classifier in these methods may lead to a serious score mismatch issue, which corresponds to the situation that the estimated scores deviate from the true ones. Such an issue causes the samples to be "},"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":"2203.14206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-27T04:37:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cad2dd96fd2fdee714d7ac952cb099074df6f7aa6df573334a9c19cab7e860f5","abstract_canon_sha256":"4d579930ad1eac27f02db3c190124069fc96feca360433dae62baad867823fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:03.731436Z","signature_b64":"WC1h5/qUQ0QBBvXYlO0Fn4DCqs/ABAJYt2YwIhtba5hf4SomUAJkAaS2YIpqitjmGjT/1pkVInGaW7j+lUlXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bdcfb416e20351ad39b6b61f0d5281d89ed7e143fda7a1cda0c223104f06621","last_reissued_at":"2026-07-05T04:09:03.731039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:03.731039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Likelihood Score Matching for Conditional Score-based Data Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo-Wun Cheng, Chen-Hao Chao, Chia-Che Chang, Chia-Ping Chen, Chun-Yi Lee, Wei-Fang Sun, Yi-Chen Lo, Yu-Lin Chang, Yu-Lun Liu","submitted_at":"2022-03-27T04:37:54Z","abstract_excerpt":"Many existing conditional score-based data generation methods utilize Bayes' theorem to decompose the gradients of a log posterior density into a mixture of scores. These methods facilitate the training procedure of conditional score models, as a mixture of scores can be separately estimated using a score model and a classifier. However, our analysis indicates that the training objectives for the classifier in these methods may lead to a serious score mismatch issue, which corresponds to the situation that the estimated scores deviate from the true ones. Such an issue causes the samples to be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14206","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/2203.14206/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":"2203.14206","created_at":"2026-07-05T04:09:03.731101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14206v1","created_at":"2026-07-05T04:09:03.731101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14206","created_at":"2026-07-05T04:09:03.731101+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPOPWQLOEA2R","created_at":"2026-07-05T04:09:03.731101+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPOPWQLOEA2RVU43","created_at":"2026-07-05T04:09:03.731101+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPOPWQLO","created_at":"2026-07-05T04:09:03.731101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08770","citing_title":"LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30346","citing_title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2304.09479","citing_title":"DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12280","citing_title":"Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07834","citing_title":"Voxify3D: Pixel Art Meets Volumetric Rendering","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23709","citing_title":"Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21860","citing_title":"Pathwise Learning of Stochastic Dynamical Systems with Partial Observations","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW","json":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW.json","graph_json":"https://pith.science/api/pith-number/JPOPWQLOEA2RVU43NNQ7BVJIDW/graph.json","events_json":"https://pith.science/api/pith-number/JPOPWQLOEA2RVU43NNQ7BVJIDW/events.json","paper":"https://pith.science/paper/JPOPWQLO"},"agent_actions":{"view_html":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW","download_json":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW.json","view_paper":"https://pith.science/paper/JPOPWQLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14206&json=true","fetch_graph":"https://pith.science/api/pith-number/JPOPWQLOEA2RVU43NNQ7BVJIDW/graph.json","fetch_events":"https://pith.science/api/pith-number/JPOPWQLOEA2RVU43NNQ7BVJIDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW/action/storage_attestation","attest_author":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW/action/author_attestation","sign_citation":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW/action/citation_signature","submit_replication":"https://pith.science/pith/JPOPWQLOEA2RVU43NNQ7BVJIDW/action/replication_record"}},"created_at":"2026-07-05T04:09:03.731101+00:00","updated_at":"2026-07-05T04:09:03.731101+00:00"}