{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:S6SOOBGWPOCZLFSZQM32IYO2QH","short_pith_number":"pith:S6SOOBGW","canonical_record":{"source":{"id":"2012.08125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T07:09:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9fbe45b2f3c2f3e47cb42940ba5f9e1d28adccbe1d9486e7d294e9b3f8c17679","abstract_canon_sha256":"31232a64759db3fb29bc650b3a0bf31ba4c663a55490e11aad9fe1e189f21677"},"schema_version":"1.0"},"canonical_sha256":"97a4e704d67b859596598337a461da81ee9a249e767ce3fa588a0d7f46bf143f","source":{"kind":"arxiv","id":"2012.08125","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08125","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08125v2","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08125","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"pith_short_12","alias_value":"S6SOOBGWPOCZ","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"S6SOOBGWPOCZLFSZ","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"S6SOOBGW","created_at":"2026-07-05T02:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:S6SOOBGWPOCZLFSZQM32IYO2QH","target":"record","payload":{"canonical_record":{"source":{"id":"2012.08125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T07:09:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9fbe45b2f3c2f3e47cb42940ba5f9e1d28adccbe1d9486e7d294e9b3f8c17679","abstract_canon_sha256":"31232a64759db3fb29bc650b3a0bf31ba4c663a55490e11aad9fe1e189f21677"},"schema_version":"1.0"},"canonical_sha256":"97a4e704d67b859596598337a461da81ee9a249e767ce3fa588a0d7f46bf143f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:53.296662Z","signature_b64":"+tgCoT9qwsq4aH8LLhzhLF2jt8ROuiKjus4jpoyYRVTs9muPWBiutECBZbwSO7eeA2clh0Bggv5iUg2ToVGBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a4e704d67b859596598337a461da81ee9a249e767ce3fa588a0d7f46bf143f","last_reissued_at":"2026-07-05T02:26:53.296220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:53.296220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.08125","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:26:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fn3Tkii4itHmnqZ3im+5lq+HVj4n8kZsyw/gxmCrm0vWj5kHh/WM6R9tGRfr6r6EbArx26wbUDe+UJVr2rtCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:46:26.910016Z"},"content_sha256":"4658022829160eb5012a99ef107aa35e0d5d64827fbafaf8959c46859c347c58","schema_version":"1.0","event_id":"sha256:4658022829160eb5012a99ef107aa35e0d5d64827fbafaf8959c46859c347c58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:S6SOOBGWPOCZLFSZQM32IYO2QH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Energy-Based Models by Diffusion Recovery Likelihood","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, Diederik P. Kingma, Ruiqi Gao, Yang Song, Ying Nian Wu","submitted_at":"2020-12-15T07:09:02Z","abstract_excerpt":"While energy-based models (EBMs) exhibit a number of desirable properties, training and sampling on high-dimensional datasets remains challenging. Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset. Each EBM is trained with recovery likelihood, which maximizes the conditional probability of the data at a certain noise level given their noisy versions at a higher noise level. Optimizing recovery likelihood is more tractable than "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08125","kind":"arxiv","version":2},"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/2012.08125/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":"2026-07-05T02:26:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r5eXHnjpy+sNjTO/2NPg97JYAdTPCAwFh53PjD9/P9pj7+w6L1c0vyXVTtwXoqGcOBrkVy/QzBMVno9qMnHWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:46:26.910689Z"},"content_sha256":"e50a47b78af50ea04933f253ad89da6e987f33cff005be853046dec69edffe14","schema_version":"1.0","event_id":"sha256:e50a47b78af50ea04933f253ad89da6e987f33cff005be853046dec69edffe14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6SOOBGWPOCZLFSZQM32IYO2QH/bundle.json","state_url":"https://pith.science/pith/S6SOOBGWPOCZLFSZQM32IYO2QH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6SOOBGWPOCZLFSZQM32IYO2QH/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":"2026-07-05T12:46:26Z","links":{"resolver":"https://pith.science/pith/S6SOOBGWPOCZLFSZQM32IYO2QH","bundle":"https://pith.science/pith/S6SOOBGWPOCZLFSZQM32IYO2QH/bundle.json","state":"https://pith.science/pith/S6SOOBGWPOCZLFSZQM32IYO2QH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6SOOBGWPOCZLFSZQM32IYO2QH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:S6SOOBGWPOCZLFSZQM32IYO2QH","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":"31232a64759db3fb29bc650b3a0bf31ba4c663a55490e11aad9fe1e189f21677","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T07:09:02Z","title_canon_sha256":"9fbe45b2f3c2f3e47cb42940ba5f9e1d28adccbe1d9486e7d294e9b3f8c17679"},"schema_version":"1.0","source":{"id":"2012.08125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08125","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08125v2","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08125","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"pith_short_12","alias_value":"S6SOOBGWPOCZ","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"S6SOOBGWPOCZLFSZ","created_at":"2026-07-05T02:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"S6SOOBGW","created_at":"2026-07-05T02:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:e50a47b78af50ea04933f253ad89da6e987f33cff005be853046dec69edffe14","target":"graph","created_at":"2026-07-05T02:26:53Z","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/2012.08125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While energy-based models (EBMs) exhibit a number of desirable properties, training and sampling on high-dimensional datasets remains challenging. Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset. Each EBM is trained with recovery likelihood, which maximizes the conditional probability of the data at a certain noise level given their noisy versions at a higher noise level. Optimizing recovery likelihood is more tractable than ","authors_text":"Ben Poole, Diederik P. Kingma, Ruiqi Gao, Yang Song, Ying Nian Wu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T07:09:02Z","title":"Learning Energy-Based Models by Diffusion Recovery Likelihood"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08125","kind":"arxiv","version":2},"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":"sha256:4658022829160eb5012a99ef107aa35e0d5d64827fbafaf8959c46859c347c58","target":"record","created_at":"2026-07-05T02:26:53Z","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":"31232a64759db3fb29bc650b3a0bf31ba4c663a55490e11aad9fe1e189f21677","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T07:09:02Z","title_canon_sha256":"9fbe45b2f3c2f3e47cb42940ba5f9e1d28adccbe1d9486e7d294e9b3f8c17679"},"schema_version":"1.0","source":{"id":"2012.08125","kind":"arxiv","version":2}},"canonical_sha256":"97a4e704d67b859596598337a461da81ee9a249e767ce3fa588a0d7f46bf143f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97a4e704d67b859596598337a461da81ee9a249e767ce3fa588a0d7f46bf143f","first_computed_at":"2026-07-05T02:26:53.296220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:53.296220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+tgCoT9qwsq4aH8LLhzhLF2jt8ROuiKjus4jpoyYRVTs9muPWBiutECBZbwSO7eeA2clh0Bggv5iUg2ToVGBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:53.296662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.08125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4658022829160eb5012a99ef107aa35e0d5d64827fbafaf8959c46859c347c58","sha256:e50a47b78af50ea04933f253ad89da6e987f33cff005be853046dec69edffe14"],"state_sha256":"a532ac00809c80bce3d2a087f380bb94cdca00f86c09ebb35acf41f4ab091fd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZomc4tNDDv+yYMfWIRU71jx9Jrh6zfLPFaXdLy7IWk9lKkB9vuH7NNRU5wNLbVhORDHLFHRpD17Xvl/n/3EBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:46:26.914192Z","bundle_sha256":"b1ff123ea3fcd78683190b7d7ddbee58ca975a50c1aa7e7d211015f4e0aa67c1"}}