{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DZ7PMTNAIR7C6DKS3JMGN5JGMR","short_pith_number":"pith:DZ7PMTNA","canonical_record":{"source":{"id":"2310.14189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T05:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"44e3a7d6224fa956d692ca60c104a827e35d4b966aa243f2cdbfb087c2522e63","abstract_canon_sha256":"c0c4eebbeba9f71bbbd2ddc91fe2f507bd630888844dc777a0b1187c3d2802a3"},"schema_version":"1.0"},"canonical_sha256":"1e7ef64da0447e2f0d52da5866f52664647a610c743df7c0168d92e2cd51d5d3","source":{"kind":"arxiv","id":"2310.14189","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14189","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14189v1","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14189","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"DZ7PMTNAIR7C","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"pith_short_16","alias_value":"DZ7PMTNAIR7C6DKS","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"pith_short_8","alias_value":"DZ7PMTNA","created_at":"2026-05-21T04:58:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DZ7PMTNAIR7C6DKS3JMGN5JGMR","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T05:33:38Z","cross_cats_sorted":[],"title_canon_sha256":"44e3a7d6224fa956d692ca60c104a827e35d4b966aa243f2cdbfb087c2522e63","abstract_canon_sha256":"c0c4eebbeba9f71bbbd2ddc91fe2f507bd630888844dc777a0b1187c3d2802a3"},"schema_version":"1.0"},"canonical_sha256":"1e7ef64da0447e2f0d52da5866f52664647a610c743df7c0168d92e2cd51d5d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T04:58:47.941359Z","signature_b64":"d3Oo25wTQSbtWPq5GFZ9gezRDNNn/aVYZr3FuCoi6TsaFGca/kY2TLwJ+ayPq8VtFXblnevE9wtwEu43p1eoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e7ef64da0447e2f0d52da5866f52664647a610c743df7c0168d92e2cd51d5d3","last_reissued_at":"2026-05-21T04:58:47.939769Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T04:58:47.939769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14189","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T04:58:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FMlct7jiq/C2m37alos1mj76d60BcAEFwTpRU4+1d+q4K1r1mm08xEfkp5UErmhxDEv16EdPXOqkK1yhkjhDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:16:17.044524Z"},"content_sha256":"ed477d138f4f9173a63a580042965d8c534d3d29a514a88fb66b49edac95cc84","schema_version":"1.0","event_id":"sha256:ed477d138f4f9173a63a580042965d8c534d3d29a514a88fb66b49edac95cc84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DZ7PMTNAIR7C6DKS3JMGN5JGMR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Techniques for Training Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Prafulla Dhariwal, Yang Song","submitted_at":"2023-10-22T05:33:38Z","abstract_excerpt":"Consistency models are a nascent family of generative models that can sample high quality data in one step without the need for adversarial training. Current consistency models achieve optimal sample quality by distilling from pre-trained diffusion models and employing learned metrics such as LPIPS. However, distillation limits the quality of consistency models to that of the pre-trained diffusion model, and LPIPS causes undesirable bias in evaluation. To tackle these challenges, we present improved techniques for consistency training, where consistency models learn directly from data without "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14189","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/2310.14189/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":"2026-05-21T04:58:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4QP/wsC/ZpBXTE+x0AxCdI+OVJ4empL7yT3C/Mdz7borx5cKLeDXMjKn9c9TLDe3TtnY9cbv5RDnLVpoeCqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:16:17.044930Z"},"content_sha256":"f173a5aad4c52cb3fbc8898bd6f923c4526d7dfa96ef221097e9b6667eee4053","schema_version":"1.0","event_id":"sha256:f173a5aad4c52cb3fbc8898bd6f923c4526d7dfa96ef221097e9b6667eee4053"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR/bundle.json","state_url":"https://pith.science/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR/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":"2026-05-26T03:16:17Z","links":{"resolver":"https://pith.science/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR","bundle":"https://pith.science/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR/bundle.json","state":"https://pith.science/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZ7PMTNAIR7C6DKS3JMGN5JGMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DZ7PMTNAIR7C6DKS3JMGN5JGMR","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":"c0c4eebbeba9f71bbbd2ddc91fe2f507bd630888844dc777a0b1187c3d2802a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T05:33:38Z","title_canon_sha256":"44e3a7d6224fa956d692ca60c104a827e35d4b966aa243f2cdbfb087c2522e63"},"schema_version":"1.0","source":{"id":"2310.14189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14189","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14189v1","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14189","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"DZ7PMTNAIR7C","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"pith_short_16","alias_value":"DZ7PMTNAIR7C6DKS","created_at":"2026-05-21T04:58:47Z"},{"alias_kind":"pith_short_8","alias_value":"DZ7PMTNA","created_at":"2026-05-21T04:58:47Z"}],"graph_snapshots":[{"event_id":"sha256:f173a5aad4c52cb3fbc8898bd6f923c4526d7dfa96ef221097e9b6667eee4053","target":"graph","created_at":"2026-05-21T04:58:47Z","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/2310.14189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consistency models are a nascent family of generative models that can sample high quality data in one step without the need for adversarial training. Current consistency models achieve optimal sample quality by distilling from pre-trained diffusion models and employing learned metrics such as LPIPS. However, distillation limits the quality of consistency models to that of the pre-trained diffusion model, and LPIPS causes undesirable bias in evaluation. To tackle these challenges, we present improved techniques for consistency training, where consistency models learn directly from data without ","authors_text":"Prafulla Dhariwal, Yang Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T05:33:38Z","title":"Improved Techniques for Training Consistency Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14189","kind":"arxiv","version":1},"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:ed477d138f4f9173a63a580042965d8c534d3d29a514a88fb66b49edac95cc84","target":"record","created_at":"2026-05-21T04:58:47Z","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":"c0c4eebbeba9f71bbbd2ddc91fe2f507bd630888844dc777a0b1187c3d2802a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T05:33:38Z","title_canon_sha256":"44e3a7d6224fa956d692ca60c104a827e35d4b966aa243f2cdbfb087c2522e63"},"schema_version":"1.0","source":{"id":"2310.14189","kind":"arxiv","version":1}},"canonical_sha256":"1e7ef64da0447e2f0d52da5866f52664647a610c743df7c0168d92e2cd51d5d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e7ef64da0447e2f0d52da5866f52664647a610c743df7c0168d92e2cd51d5d3","first_computed_at":"2026-05-21T04:58:47.939769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T04:58:47.939769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d3Oo25wTQSbtWPq5GFZ9gezRDNNn/aVYZr3FuCoi6TsaFGca/kY2TLwJ+ayPq8VtFXblnevE9wtwEu43p1eoDA==","signature_status":"signed_v1","signed_at":"2026-05-21T04:58:47.941359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed477d138f4f9173a63a580042965d8c534d3d29a514a88fb66b49edac95cc84","sha256:f173a5aad4c52cb3fbc8898bd6f923c4526d7dfa96ef221097e9b6667eee4053"],"state_sha256":"3de16d71ede6356c8d8496c170595268cc9937463be2946ef23f04a457f7d3f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUhjoR7M0tCzpeQ53uXovA26id8BPtXqwi9mD30eY9J0axTUheNZzSHkLOO3sFjlxdmElKlSuTqaAOm5L+cICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:16:17.047609Z","bundle_sha256":"b9a29ec0c79f44061876847982316401b26d1f4d2b0c0c68c016bad3196d6bc1"}}