{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Y5QQOWQFHRLH6OXMGD45WM7YBW","short_pith_number":"pith:Y5QQOWQF","canonical_record":{"source":{"id":"2107.01131","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-02T15:20:41Z","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"2787df738aa3a40626e52c68075ab9bc358f921816f33d72e9d0aef4bb22919b","abstract_canon_sha256":"61d6c1617c0d72fb31ab566e28b3d84498141896419b501559dfe4a75846398f"},"schema_version":"1.0"},"canonical_sha256":"c761075a053c567f3aec30f9db33f80d98e947575142001b753c23afa3066bee","source":{"kind":"arxiv","id":"2107.01131","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01131","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01131v3","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01131","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y5QQOWQFHRLH","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y5QQOWQFHRLH6OXM","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y5QQOWQF","created_at":"2026-07-05T05:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Y5QQOWQFHRLH6OXMGD45WM7YBW","target":"record","payload":{"canonical_record":{"source":{"id":"2107.01131","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-02T15:20:41Z","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"2787df738aa3a40626e52c68075ab9bc358f921816f33d72e9d0aef4bb22919b","abstract_canon_sha256":"61d6c1617c0d72fb31ab566e28b3d84498141896419b501559dfe4a75846398f"},"schema_version":"1.0"},"canonical_sha256":"c761075a053c567f3aec30f9db33f80d98e947575142001b753c23afa3066bee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:12.423987Z","signature_b64":"VQvKW1wE7+5WJrZhDvSdbna+cFVPn8oZcsPNOOizQKrA6kV/R2PRP0AE439NnRv+mP9TcyTtjNXpAZ+L4nF0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c761075a053c567f3aec30f9db33f80d98e947575142001b753c23afa3066bee","last_reissued_at":"2026-07-05T05:09:12.423547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:12.423547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.01131","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SGOhA4pn3pw2TSrcugxyr8PP52d6YXQZPBOKngprd/g9f/GnMW3MpipfSU5uMO7/Y/4aJT4hG0ixp5pu7d0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:41:16.206786Z"},"content_sha256":"a72d86c804fdb2b9dc68d685f7d9ddc1542229eab38be2abdd5d5f630c3ca0f7","schema_version":"1.0","event_id":"sha256:a72d86c804fdb2b9dc68d685f7d9ddc1542229eab38be2abdd5d5f630c3ca0f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Y5QQOWQFHRLH6OXMGD45WM7YBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Chenyang Tao, Dong Wang, Fan Li, Jing Huang, Junya Chen, Lawrence Carin, Qing Guo, Xinwei Deng, Yuewei Yang","submitted_at":"2021-07-02T15:20:41Z","abstract_excerpt":"Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning. While featuring superior stability, these estimators crucially depend on costly large-batch training, and they sacrifice bound tightness for variance reduction. To overcome these limitations, we revisit the mathematics of popular variational MI bounds from the lens of unnormalized statistical modeling and convex optimization. Our investigation not only yields a new unified theoretical framework encompassing popular variational MI bounds"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01131","kind":"arxiv","version":3},"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/2107.01131/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":"2026-07-05T05:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBl0QcpjbB+kFD3d5zluKh77pcLYvJJZYFn3AIWvHv/s/4rkq9DA8bczcqVaJ18MechmNkSjW/BmTZq70meQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:41:16.207394Z"},"content_sha256":"88eaf457fae34d34836e21a5599bbbecb65d006b0875368719954d040010b236","schema_version":"1.0","event_id":"sha256:88eaf457fae34d34836e21a5599bbbecb65d006b0875368719954d040010b236"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW/bundle.json","state_url":"https://pith.science/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW/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":"2026-08-03T15:41:16Z","links":{"resolver":"https://pith.science/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW","bundle":"https://pith.science/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW/bundle.json","state":"https://pith.science/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5QQOWQFHRLH6OXMGD45WM7YBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Y5QQOWQFHRLH6OXMGD45WM7YBW","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":"61d6c1617c0d72fb31ab566e28b3d84498141896419b501559dfe4a75846398f","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-02T15:20:41Z","title_canon_sha256":"2787df738aa3a40626e52c68075ab9bc358f921816f33d72e9d0aef4bb22919b"},"schema_version":"1.0","source":{"id":"2107.01131","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01131","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01131v3","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01131","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y5QQOWQFHRLH","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y5QQOWQFHRLH6OXM","created_at":"2026-07-05T05:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y5QQOWQF","created_at":"2026-07-05T05:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:88eaf457fae34d34836e21a5599bbbecb65d006b0875368719954d040010b236","target":"graph","created_at":"2026-07-05T05:09:12Z","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/2107.01131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning. While featuring superior stability, these estimators crucially depend on costly large-batch training, and they sacrifice bound tightness for variance reduction. To overcome these limitations, we revisit the mathematics of popular variational MI bounds from the lens of unnormalized statistical modeling and convex optimization. Our investigation not only yields a new unified theoretical framework encompassing popular variational MI bounds","authors_text":"Chenyang Tao, Dong Wang, Fan Li, Jing Huang, Junya Chen, Lawrence Carin, Qing Guo, Xinwei Deng, Yuewei Yang","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-02T15:20:41Z","title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01131","kind":"arxiv","version":3},"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:a72d86c804fdb2b9dc68d685f7d9ddc1542229eab38be2abdd5d5f630c3ca0f7","target":"record","created_at":"2026-07-05T05:09:12Z","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":"61d6c1617c0d72fb31ab566e28b3d84498141896419b501559dfe4a75846398f","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-07-02T15:20:41Z","title_canon_sha256":"2787df738aa3a40626e52c68075ab9bc358f921816f33d72e9d0aef4bb22919b"},"schema_version":"1.0","source":{"id":"2107.01131","kind":"arxiv","version":3}},"canonical_sha256":"c761075a053c567f3aec30f9db33f80d98e947575142001b753c23afa3066bee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c761075a053c567f3aec30f9db33f80d98e947575142001b753c23afa3066bee","first_computed_at":"2026-07-05T05:09:12.423547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:12.423547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VQvKW1wE7+5WJrZhDvSdbna+cFVPn8oZcsPNOOizQKrA6kV/R2PRP0AE439NnRv+mP9TcyTtjNXpAZ+L4nF0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:12.423987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01131","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a72d86c804fdb2b9dc68d685f7d9ddc1542229eab38be2abdd5d5f630c3ca0f7","sha256:88eaf457fae34d34836e21a5599bbbecb65d006b0875368719954d040010b236"],"state_sha256":"35737afe083e5dcaefe623cbe3916daeddd15827c8a1abad83e5c732513376e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0cKNPYAzwRxbZ8H/iCLHhkedvNX19fHOcWoEu4c8ZwebzzwEajSEPftCOADlz3664+FDxkt2q3ErvFiRo8gBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:41:16.215388Z","bundle_sha256":"1e3267a2a6c87593b915117d303dd3e25280e9935e6d2199d5567324f151a435"}}