{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IJHWFYFPXFFBWZLCCSBREHF3DP","short_pith_number":"pith:IJHWFYFP","canonical_record":{"source":{"id":"2502.09609","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:57:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3d1ec09d06ba50de77602f01683261cd703e236da720c94c5f94b95312f29d50","abstract_canon_sha256":"719f4dc763a2907033bfc68a63a1929cb686ee12eaee1fd89f63e2b7a16d3ccd"},"schema_version":"1.0"},"canonical_sha256":"424f62e0afb94a1b65621483121cbb1bd7e28b2c95886b0686be1aad673da4ed","source":{"kind":"arxiv","id":"2502.09609","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09609","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09609v3","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09609","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"IJHWFYFPXFFB","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"IJHWFYFPXFFBWZLC","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"IJHWFYFP","created_at":"2026-07-05T11:36:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IJHWFYFPXFFBWZLCCSBREHF3DP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09609","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:57:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3d1ec09d06ba50de77602f01683261cd703e236da720c94c5f94b95312f29d50","abstract_canon_sha256":"719f4dc763a2907033bfc68a63a1929cb686ee12eaee1fd89f63e2b7a16d3ccd"},"schema_version":"1.0"},"canonical_sha256":"424f62e0afb94a1b65621483121cbb1bd7e28b2c95886b0686be1aad673da4ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:55.385961Z","signature_b64":"kPsryYArWVAu6QfCQ02X5yT0j0icPR5yvxFWWQCVTbuBaJX8TMydp3vvWMv/iTC0IXKv3keempY131pKqYz2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"424f62e0afb94a1b65621483121cbb1bd7e28b2c95886b0686be1aad673da4ed","last_reissued_at":"2026-07-05T11:36:55.385435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:55.385435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09609","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiAycsDqgoZTQ7vwpWKz7uN76RW0+RtPnPrR8rNMT9IkHUZoy85/ixbSCRj1RzIp5i1CivX5u7DboJnApQ85DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:56.604079Z"},"content_sha256":"8b0957d12b72909b27933525259c5bfe4d8c6dad19d17497debcb029ef13ef22","schema_version":"1.0","event_id":"sha256:8b0957d12b72909b27933525259c5bfe4d8c6dad19d17497debcb029ef13ef22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IJHWFYFPXFFBWZLCCSBREHF3DP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregory Wornell, J. Jon Ryu, Tejas Jayashankar","submitted_at":"2025-02-13T18:57:20Z","abstract_excerpt":"We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models by minimizing a class of divergences called the $\\alpha$-skew Jensen--Shannon divergence. At its core, SMT estimates the score of mixture distributions between real and fake samples across multiple noise levels. Similar to consistency models, our approach supports both training from scratch (SMT) and distillation using a pretrained diffusion model, which we call Score-of-Mixture Distillation (SMD). It is simple to implement, requires minimal hyperparameter tuning, and ensures stable training. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09609","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/2502.09609/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZTHYCaXBDVHCmiCgbtaKp84FzydLgXNYXEo+Xo12tjjTsEUOJfjvwiQjHwhRp7QBT/i0hy3fIXhkGSUQVz3TBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:56.604659Z"},"content_sha256":"689a6634aacd54352e3c9308788b3ab2d3c6ff521128b0849a84999ca9ef1b40","schema_version":"1.0","event_id":"sha256:689a6634aacd54352e3c9308788b3ab2d3c6ff521128b0849a84999ca9ef1b40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJHWFYFPXFFBWZLCCSBREHF3DP/bundle.json","state_url":"https://pith.science/pith/IJHWFYFPXFFBWZLCCSBREHF3DP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJHWFYFPXFFBWZLCCSBREHF3DP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T12:12:56Z","links":{"resolver":"https://pith.science/pith/IJHWFYFPXFFBWZLCCSBREHF3DP","bundle":"https://pith.science/pith/IJHWFYFPXFFBWZLCCSBREHF3DP/bundle.json","state":"https://pith.science/pith/IJHWFYFPXFFBWZLCCSBREHF3DP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJHWFYFPXFFBWZLCCSBREHF3DP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IJHWFYFPXFFBWZLCCSBREHF3DP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"719f4dc763a2907033bfc68a63a1929cb686ee12eaee1fd89f63e2b7a16d3ccd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:57:20Z","title_canon_sha256":"3d1ec09d06ba50de77602f01683261cd703e236da720c94c5f94b95312f29d50"},"schema_version":"1.0","source":{"id":"2502.09609","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09609","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09609v3","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09609","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"IJHWFYFPXFFB","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"IJHWFYFPXFFBWZLC","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"IJHWFYFP","created_at":"2026-07-05T11:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:689a6634aacd54352e3c9308788b3ab2d3c6ff521128b0849a84999ca9ef1b40","target":"graph","created_at":"2026-07-05T11:36:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.09609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models by minimizing a class of divergences called the $\\alpha$-skew Jensen--Shannon divergence. At its core, SMT estimates the score of mixture distributions between real and fake samples across multiple noise levels. Similar to consistency models, our approach supports both training from scratch (SMT) and distillation using a pretrained diffusion model, which we call Score-of-Mixture Distillation (SMD). It is simple to implement, requires minimal hyperparameter tuning, and ensures stable training. ","authors_text":"Gregory Wornell, J. Jon Ryu, Tejas Jayashankar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:57:20Z","title":"Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09609","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8b0957d12b72909b27933525259c5bfe4d8c6dad19d17497debcb029ef13ef22","target":"record","created_at":"2026-07-05T11:36:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"719f4dc763a2907033bfc68a63a1929cb686ee12eaee1fd89f63e2b7a16d3ccd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:57:20Z","title_canon_sha256":"3d1ec09d06ba50de77602f01683261cd703e236da720c94c5f94b95312f29d50"},"schema_version":"1.0","source":{"id":"2502.09609","kind":"arxiv","version":3}},"canonical_sha256":"424f62e0afb94a1b65621483121cbb1bd7e28b2c95886b0686be1aad673da4ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"424f62e0afb94a1b65621483121cbb1bd7e28b2c95886b0686be1aad673da4ed","first_computed_at":"2026-07-05T11:36:55.385435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:55.385435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kPsryYArWVAu6QfCQ02X5yT0j0icPR5yvxFWWQCVTbuBaJX8TMydp3vvWMv/iTC0IXKv3keempY131pKqYz2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:55.385961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09609","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b0957d12b72909b27933525259c5bfe4d8c6dad19d17497debcb029ef13ef22","sha256:689a6634aacd54352e3c9308788b3ab2d3c6ff521128b0849a84999ca9ef1b40"],"state_sha256":"ee1b09c46d38e2b6cbefe33ead797632f5e45a4b3842bdebced8bb74a9160a80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrJWpHogyLQEwUSXpzzDGrmtqHol9S2WKLqYCwSeHWCEfJdbi09T0KpAliLQHD87TKifeaA++9KgbBHbPHtDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:12:56.610275Z","bundle_sha256":"b7b4f4218ea1d0e50d5294ee4f2b7eeae0591286329bc5dccbf692170dad0ccb"}}