{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LVDNQIPFDY6FGIT624KPD6VURB","short_pith_number":"pith:LVDNQIPF","canonical_record":{"source":{"id":"2210.10715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T16:47:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c680316d205cb1052e35562653c1fb08c719718b1fd3a46694342fdf511da09d","abstract_canon_sha256":"632a91b1733ac203dc1ed743481acd73a9eb0ecd5c8a9a774f1305b9d7362ff8"},"schema_version":"1.0"},"canonical_sha256":"5d46d821e51e3c53227ed714f1fab48847b124f6a5020aa8dfab0437d4a0cb29","source":{"kind":"arxiv","id":"2210.10715","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10715","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10715v1","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10715","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"pith_short_12","alias_value":"LVDNQIPFDY6F","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"pith_short_16","alias_value":"LVDNQIPFDY6FGIT6","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"pith_short_8","alias_value":"LVDNQIPF","created_at":"2026-07-05T05:08:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LVDNQIPFDY6FGIT624KPD6VURB","target":"record","payload":{"canonical_record":{"source":{"id":"2210.10715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T16:47:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c680316d205cb1052e35562653c1fb08c719718b1fd3a46694342fdf511da09d","abstract_canon_sha256":"632a91b1733ac203dc1ed743481acd73a9eb0ecd5c8a9a774f1305b9d7362ff8"},"schema_version":"1.0"},"canonical_sha256":"5d46d821e51e3c53227ed714f1fab48847b124f6a5020aa8dfab0437d4a0cb29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:23.008455Z","signature_b64":"K1JcDpgMODftx1omBFkCaqG3f3Pp3qwcaQvFTXZjFMm1sl4UWPLN/q2U6RfeTeoMMJE1x+UwwzOce+wYiZV3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d46d821e51e3c53227ed714f1fab48847b124f6a5020aa8dfab0437d4a0cb29","last_reissued_at":"2026-07-05T05:08:23.008001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:23.008001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.10715","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":"2026-07-05T05:08:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSKBMh9wQtqCQszBmn2hGRT0Er5LyVT16jcQqAPoeCoKIY5hGVY3sVWreG6Wq6Uy9pcHMPZ4cCS+cnFcBXH8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T01:14:11.129594Z"},"content_sha256":"d06c99e43507bae5e95e9587a4b660e062db3b89ad8557f564cc1626961c8ef3","schema_version":"1.0","event_id":"sha256:d06c99e43507bae5e95e9587a4b660e062db3b89ad8557f564cc1626961c8ef3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LVDNQIPFDY6FGIT624KPD6VURB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autoregressive Generative Modeling with Noise Conditional Maximum Likelihood Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Henry Li, Yuval Kluger","submitted_at":"2022-10-19T16:47:51Z","abstract_excerpt":"We introduce a simple modification to the standard maximum likelihood estimation (MLE) framework. Rather than maximizing a single unconditional likelihood of the data under the model, we maximize a family of \\textit{noise conditional} likelihoods consisting of the data perturbed by a continuum of noise levels. We find that models trained this way are more robust to noise, obtain higher test likelihoods, and generate higher quality images. They can also be sampled from via a novel score-based sampling scheme which combats the classical \\textit{covariate shift} problem that occurs during sample "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10715","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/2210.10715/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":"2026-07-05T05:08:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7Jhihj1RGFmkd/Kz751x9WjmTT3DCFvLR4gERs4feO7KVhNtmNDwmRy2NOeI+IJyXRvPRV8cE78qcNqFLx7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T01:14:11.129971Z"},"content_sha256":"77b826502b26992e94a5a4ed2768504f090b4241968750f3803051fd2799b6fe","schema_version":"1.0","event_id":"sha256:77b826502b26992e94a5a4ed2768504f090b4241968750f3803051fd2799b6fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LVDNQIPFDY6FGIT624KPD6VURB/bundle.json","state_url":"https://pith.science/pith/LVDNQIPFDY6FGIT624KPD6VURB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LVDNQIPFDY6FGIT624KPD6VURB/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":"2026-07-14T01:14:11Z","links":{"resolver":"https://pith.science/pith/LVDNQIPFDY6FGIT624KPD6VURB","bundle":"https://pith.science/pith/LVDNQIPFDY6FGIT624KPD6VURB/bundle.json","state":"https://pith.science/pith/LVDNQIPFDY6FGIT624KPD6VURB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LVDNQIPFDY6FGIT624KPD6VURB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LVDNQIPFDY6FGIT624KPD6VURB","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":"632a91b1733ac203dc1ed743481acd73a9eb0ecd5c8a9a774f1305b9d7362ff8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T16:47:51Z","title_canon_sha256":"c680316d205cb1052e35562653c1fb08c719718b1fd3a46694342fdf511da09d"},"schema_version":"1.0","source":{"id":"2210.10715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10715","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10715v1","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10715","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"pith_short_12","alias_value":"LVDNQIPFDY6F","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"pith_short_16","alias_value":"LVDNQIPFDY6FGIT6","created_at":"2026-07-05T05:08:23Z"},{"alias_kind":"pith_short_8","alias_value":"LVDNQIPF","created_at":"2026-07-05T05:08:23Z"}],"graph_snapshots":[{"event_id":"sha256:77b826502b26992e94a5a4ed2768504f090b4241968750f3803051fd2799b6fe","target":"graph","created_at":"2026-07-05T05:08:23Z","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/2210.10715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a simple modification to the standard maximum likelihood estimation (MLE) framework. Rather than maximizing a single unconditional likelihood of the data under the model, we maximize a family of \\textit{noise conditional} likelihoods consisting of the data perturbed by a continuum of noise levels. We find that models trained this way are more robust to noise, obtain higher test likelihoods, and generate higher quality images. They can also be sampled from via a novel score-based sampling scheme which combats the classical \\textit{covariate shift} problem that occurs during sample ","authors_text":"Henry Li, Yuval Kluger","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T16:47:51Z","title":"Autoregressive Generative Modeling with Noise Conditional Maximum Likelihood Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10715","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:d06c99e43507bae5e95e9587a4b660e062db3b89ad8557f564cc1626961c8ef3","target":"record","created_at":"2026-07-05T05:08:23Z","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":"632a91b1733ac203dc1ed743481acd73a9eb0ecd5c8a9a774f1305b9d7362ff8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T16:47:51Z","title_canon_sha256":"c680316d205cb1052e35562653c1fb08c719718b1fd3a46694342fdf511da09d"},"schema_version":"1.0","source":{"id":"2210.10715","kind":"arxiv","version":1}},"canonical_sha256":"5d46d821e51e3c53227ed714f1fab48847b124f6a5020aa8dfab0437d4a0cb29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d46d821e51e3c53227ed714f1fab48847b124f6a5020aa8dfab0437d4a0cb29","first_computed_at":"2026-07-05T05:08:23.008001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:23.008001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K1JcDpgMODftx1omBFkCaqG3f3Pp3qwcaQvFTXZjFMm1sl4UWPLN/q2U6RfeTeoMMJE1x+UwwzOce+wYiZV3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:23.008455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.10715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d06c99e43507bae5e95e9587a4b660e062db3b89ad8557f564cc1626961c8ef3","sha256:77b826502b26992e94a5a4ed2768504f090b4241968750f3803051fd2799b6fe"],"state_sha256":"809f82ab506b2ea85565b8e8e4abd49b4ca9229a1418e2fb1024cc0597aad175"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIjS4DwymsgBnj24Na2rfRMLf2BUP4VKVWcPjQDKgwtkGuCBvNMj0onOkP5UnbuPEaTgsW3Vsh5OYhMINUwoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T01:14:11.132116Z","bundle_sha256":"b278abe76779ef626aa41181bdda9af83a64b9bd4003d95e4b246e6f4deef0a4"}}