{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GABRRTTVRZZLIY2UC4SKE2VVUA","short_pith_number":"pith:GABRRTTV","canonical_record":{"source":{"id":"2212.00362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T08:44:21Z","cross_cats_sorted":[],"title_canon_sha256":"64608066f6081220c75c74cf45e4c1b13b6504ebfa58202789f828f363c56c14","abstract_canon_sha256":"07507963892a1e7f7e7579bd6acd4402e084905e356a33ec6ef56b81e734d7ed"},"schema_version":"1.0"},"canonical_sha256":"300318ce758e72b463541724a26ab5a0013a2388950e615be88e6e2fbdf8428b","source":{"kind":"arxiv","id":"2212.00362","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00362","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00362v1","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00362","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"GABRRTTVRZZL","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"pith_short_16","alias_value":"GABRRTTVRZZLIY2U","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"pith_short_8","alias_value":"GABRRTTV","created_at":"2026-07-05T05:21:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GABRRTTVRZZLIY2UC4SKE2VVUA","target":"record","payload":{"canonical_record":{"source":{"id":"2212.00362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T08:44:21Z","cross_cats_sorted":[],"title_canon_sha256":"64608066f6081220c75c74cf45e4c1b13b6504ebfa58202789f828f363c56c14","abstract_canon_sha256":"07507963892a1e7f7e7579bd6acd4402e084905e356a33ec6ef56b81e734d7ed"},"schema_version":"1.0"},"canonical_sha256":"300318ce758e72b463541724a26ab5a0013a2388950e615be88e6e2fbdf8428b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:33.501095Z","signature_b64":"VzDVSVyOig5vYZJasyGGP3DalB0wefYHnvxo0LOElBkPuRnYxueAJArVhSHUEQO8zHcLkHSbIaCH9FH2ztmgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300318ce758e72b463541724a26ab5a0013a2388950e615be88e6e2fbdf8428b","last_reissued_at":"2026-07-05T05:21:33.500686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:33.500686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.00362","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":"2026-07-05T05:21:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDjNgO+GtZ0W3GOzKqg3OCw1vo6urt39t1kLnK+4+xmBJ4KcD7sz0S6n5czu9pNPqzKDEsB1q7Wv6xMRKkcnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:30:25.101121Z"},"content_sha256":"ac8cfdc181cedfe85d6f3783cbd9ff41ee8da2b57d1580dc5da26977d35ff850","schema_version":"1.0","event_id":"sha256:ac8cfdc181cedfe85d6f3783cbd9ff41ee8da2b57d1580dc5da26977d35ff850"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GABRRTTVRZZLIY2UC4SKE2VVUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Are Conditional Generative Models Better Than Unconditional Ones?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chongxuan Li, Fan Bao, Jiacheng Sun, Jun Zhu","submitted_at":"2022-12-01T08:44:21Z","abstract_excerpt":"Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data. So do score-based diffusion models. In this paper, we analyze the phenomenon formally and identify that the key of conditional learning is to partition the data properly. Inspired by the analyses, we propose self-conditioned diffusion models (SCDM), which is trained conditioned on indices clustered by the k-means algorithm on the features extracted by a model pre-trained in a self-supervised manner. SCDM significantly impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00362","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/2212.00362/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":"2026-07-05T05:21:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyjWYRaqAxywZan7HYisX1RlaP57z4o+IVu0vckssYU3xwkVdwdtBQMAhcn1G94mVBEpOrxMT5bG/0gnr8shAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:30:25.101742Z"},"content_sha256":"ad57591921e9ec22961bab35b2dd62af126b44af1ebe6e3d263d7a8b973a0896","schema_version":"1.0","event_id":"sha256:ad57591921e9ec22961bab35b2dd62af126b44af1ebe6e3d263d7a8b973a0896"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GABRRTTVRZZLIY2UC4SKE2VVUA/bundle.json","state_url":"https://pith.science/pith/GABRRTTVRZZLIY2UC4SKE2VVUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GABRRTTVRZZLIY2UC4SKE2VVUA/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":"2026-08-12T14:30:25Z","links":{"resolver":"https://pith.science/pith/GABRRTTVRZZLIY2UC4SKE2VVUA","bundle":"https://pith.science/pith/GABRRTTVRZZLIY2UC4SKE2VVUA/bundle.json","state":"https://pith.science/pith/GABRRTTVRZZLIY2UC4SKE2VVUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GABRRTTVRZZLIY2UC4SKE2VVUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GABRRTTVRZZLIY2UC4SKE2VVUA","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":"07507963892a1e7f7e7579bd6acd4402e084905e356a33ec6ef56b81e734d7ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T08:44:21Z","title_canon_sha256":"64608066f6081220c75c74cf45e4c1b13b6504ebfa58202789f828f363c56c14"},"schema_version":"1.0","source":{"id":"2212.00362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00362","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00362v1","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00362","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"GABRRTTVRZZL","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"pith_short_16","alias_value":"GABRRTTVRZZLIY2U","created_at":"2026-07-05T05:21:33Z"},{"alias_kind":"pith_short_8","alias_value":"GABRRTTV","created_at":"2026-07-05T05:21:33Z"}],"graph_snapshots":[{"event_id":"sha256:ad57591921e9ec22961bab35b2dd62af126b44af1ebe6e3d263d7a8b973a0896","target":"graph","created_at":"2026-07-05T05:21:33Z","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/2212.00362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data. So do score-based diffusion models. In this paper, we analyze the phenomenon formally and identify that the key of conditional learning is to partition the data properly. Inspired by the analyses, we propose self-conditioned diffusion models (SCDM), which is trained conditioned on indices clustered by the k-means algorithm on the features extracted by a model pre-trained in a self-supervised manner. SCDM significantly impr","authors_text":"Chongxuan Li, Fan Bao, Jiacheng Sun, Jun Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T08:44:21Z","title":"Why Are Conditional Generative Models Better Than Unconditional Ones?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00362","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:ac8cfdc181cedfe85d6f3783cbd9ff41ee8da2b57d1580dc5da26977d35ff850","target":"record","created_at":"2026-07-05T05:21:33Z","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":"07507963892a1e7f7e7579bd6acd4402e084905e356a33ec6ef56b81e734d7ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T08:44:21Z","title_canon_sha256":"64608066f6081220c75c74cf45e4c1b13b6504ebfa58202789f828f363c56c14"},"schema_version":"1.0","source":{"id":"2212.00362","kind":"arxiv","version":1}},"canonical_sha256":"300318ce758e72b463541724a26ab5a0013a2388950e615be88e6e2fbdf8428b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"300318ce758e72b463541724a26ab5a0013a2388950e615be88e6e2fbdf8428b","first_computed_at":"2026-07-05T05:21:33.500686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:33.500686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VzDVSVyOig5vYZJasyGGP3DalB0wefYHnvxo0LOElBkPuRnYxueAJArVhSHUEQO8zHcLkHSbIaCH9FH2ztmgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:33.501095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac8cfdc181cedfe85d6f3783cbd9ff41ee8da2b57d1580dc5da26977d35ff850","sha256:ad57591921e9ec22961bab35b2dd62af126b44af1ebe6e3d263d7a8b973a0896"],"state_sha256":"e6910c1dad0c56bc91169b4ca918dfc5338834a1c7f82def37f0a41fc968e44d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"En4eCv5wc/SmFJGkdNj4J7oXEHOzLtqgm3FTr0Wi8mURivaKwXFrtYfJUDLLIDtr+hJ0xAJovl9KlSq0SQPDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:30:25.109364Z","bundle_sha256":"03a68765f6e2e8747871e8b11ee4f92c43c2acab756560534b94dfb048e21f9c"}}