{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:K2UB5W4EHW2QNSNI6ICOP4XXLY","short_pith_number":"pith:K2UB5W4E","canonical_record":{"source":{"id":"2012.15480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T07:13:58Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"37b4b444d6ed61a068b348a6c23eaf7ce73b4af20ad50dde931a3d3daa0e5cb1","abstract_canon_sha256":"5781603e591258766641de26d66e238601b0ef8aee380468273bd8b5ecc63b48"},"schema_version":"1.0"},"canonical_sha256":"56a81edb843db506c9a8f204e7f2f75e2d178b4021fa98c34ccf45fefb7232b2","source":{"kind":"arxiv","id":"2012.15480","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15480","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15480v2","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15480","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"K2UB5W4EHW2Q","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"K2UB5W4EHW2QNSNI","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"K2UB5W4E","created_at":"2026-07-05T02:07:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:K2UB5W4EHW2QNSNI6ICOP4XXLY","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T07:13:58Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"37b4b444d6ed61a068b348a6c23eaf7ce73b4af20ad50dde931a3d3daa0e5cb1","abstract_canon_sha256":"5781603e591258766641de26d66e238601b0ef8aee380468273bd8b5ecc63b48"},"schema_version":"1.0"},"canonical_sha256":"56a81edb843db506c9a8f204e7f2f75e2d178b4021fa98c34ccf45fefb7232b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:06.231881Z","signature_b64":"O36dd/YEeV3BBQvlQrP1roBnOtfk1qoUDymrrnvYX0cfNszCCV7gpV7LAbC58zDPk60KybFirnF4zSMyQvptBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56a81edb843db506c9a8f204e7f2f75e2d178b4021fa98c34ccf45fefb7232b2","last_reissued_at":"2026-07-05T02:07:06.231432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:06.231432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15480","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":"2026-07-05T02:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CQeqHD9gaZC7H6waasmtlg2UMSUKGHYQrsEyhq67y5ry+a4zqIlZW/b6MByholnl/I52WVW07nCQeQsQ0eaPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:27:43.425559Z"},"content_sha256":"128f42cbdfaa909ab5bc0c1f4e1b151286b46fdcbe7b669473c027254849d5e5","schema_version":"1.0","event_id":"sha256:128f42cbdfaa909ab5bc0c1f4e1b151286b46fdcbe7b669473c027254849d5e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:K2UB5W4EHW2QNSNI6ICOP4XXLY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Likelihood Ratio Exponential Families","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Makhzani, Aram Galstyan, Frank Nielsen, Greg Ver Steeg, Rob Brekelmans","submitted_at":"2020-12-31T07:13:58Z","abstract_excerpt":"The exponential family is well known in machine learning and statistical physics as the maximum entropy distribution subject to a set of observed constraints, while the geometric mixture path is common in MCMC methods such as annealed importance sampling. Linking these two ideas, recent work has interpreted the geometric mixture path as an exponential family of distributions to analyze the thermodynamic variational objective (TVO).\n  We extend these likelihood ratio exponential families to include solutions to rate-distortion (RD) optimization, the information bottleneck (IB) method, and recen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15480","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/2012.15480/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":"2026-07-05T02:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdwXbJwGIEShI6dYqPBvXvKOO2RDzTSMh+kVqL0K3a6T07XP7sQtKyMID4lQQuYZ/6FOguQdHbjWG05YQ7yuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:27:43.426101Z"},"content_sha256":"1802a8326ff00ebed3154bd4abff173f53e133b08772f633dd3fa91308481232","schema_version":"1.0","event_id":"sha256:1802a8326ff00ebed3154bd4abff173f53e133b08772f633dd3fa91308481232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY/bundle.json","state_url":"https://pith.science/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY/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":"2026-08-18T18:27:43Z","links":{"resolver":"https://pith.science/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY","bundle":"https://pith.science/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY/bundle.json","state":"https://pith.science/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2UB5W4EHW2QNSNI6ICOP4XXLY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:K2UB5W4EHW2QNSNI6ICOP4XXLY","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":"5781603e591258766641de26d66e238601b0ef8aee380468273bd8b5ecc63b48","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T07:13:58Z","title_canon_sha256":"37b4b444d6ed61a068b348a6c23eaf7ce73b4af20ad50dde931a3d3daa0e5cb1"},"schema_version":"1.0","source":{"id":"2012.15480","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15480","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15480v2","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15480","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"K2UB5W4EHW2Q","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"K2UB5W4EHW2QNSNI","created_at":"2026-07-05T02:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"K2UB5W4E","created_at":"2026-07-05T02:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:1802a8326ff00ebed3154bd4abff173f53e133b08772f633dd3fa91308481232","target":"graph","created_at":"2026-07-05T02:07:06Z","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/2012.15480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exponential family is well known in machine learning and statistical physics as the maximum entropy distribution subject to a set of observed constraints, while the geometric mixture path is common in MCMC methods such as annealed importance sampling. Linking these two ideas, recent work has interpreted the geometric mixture path as an exponential family of distributions to analyze the thermodynamic variational objective (TVO).\n  We extend these likelihood ratio exponential families to include solutions to rate-distortion (RD) optimization, the information bottleneck (IB) method, and recen","authors_text":"Alireza Makhzani, Aram Galstyan, Frank Nielsen, Greg Ver Steeg, Rob Brekelmans","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T07:13:58Z","title":"Likelihood Ratio Exponential Families"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15480","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":"sha256:128f42cbdfaa909ab5bc0c1f4e1b151286b46fdcbe7b669473c027254849d5e5","target":"record","created_at":"2026-07-05T02:07:06Z","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":"5781603e591258766641de26d66e238601b0ef8aee380468273bd8b5ecc63b48","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T07:13:58Z","title_canon_sha256":"37b4b444d6ed61a068b348a6c23eaf7ce73b4af20ad50dde931a3d3daa0e5cb1"},"schema_version":"1.0","source":{"id":"2012.15480","kind":"arxiv","version":2}},"canonical_sha256":"56a81edb843db506c9a8f204e7f2f75e2d178b4021fa98c34ccf45fefb7232b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56a81edb843db506c9a8f204e7f2f75e2d178b4021fa98c34ccf45fefb7232b2","first_computed_at":"2026-07-05T02:07:06.231432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:07:06.231432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O36dd/YEeV3BBQvlQrP1roBnOtfk1qoUDymrrnvYX0cfNszCCV7gpV7LAbC58zDPk60KybFirnF4zSMyQvptBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:07:06.231881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15480","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:128f42cbdfaa909ab5bc0c1f4e1b151286b46fdcbe7b669473c027254849d5e5","sha256:1802a8326ff00ebed3154bd4abff173f53e133b08772f633dd3fa91308481232"],"state_sha256":"079bf19b6998203761a81fe8ab165f5893b96f5ab0e555093ead2b402772305d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Dsveh3scrtITkC6ci0m8u1DLjVW4LnEHGI6F/5lcTNw7xsaqFjHnNDt2EvvTffOx8T6agxMxEtuwIy13Bq3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:27:43.431334Z","bundle_sha256":"6e7070c6078218500e5f14c476f5606b0ce3b8b705f76144ba65fa5ab329f8fa"}}