{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Z2B63U6FHNBVQ2Q7MW7R3YLCK5","short_pith_number":"pith:Z2B63U6F","canonical_record":{"source":{"id":"2305.08013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-13T21:44:32Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"a0c34c78f01afd452fe47a60967a9d27bc1efc90fb6a1d15512e648d66ba693c","abstract_canon_sha256":"5186bb9e1ee40d32339beb197de6d3309142dc1ea654d10e8a036a5b41cf39fe"},"schema_version":"1.0"},"canonical_sha256":"ce83edd3c53b43586a1f65bf1de16257707315c836fb21b3f16f268653e45a4e","source":{"kind":"arxiv","id":"2305.08013","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08013","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08013v2","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08013","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z2B63U6FHNBV","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z2B63U6FHNBVQ2Q7","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z2B63U6F","created_at":"2026-07-05T08:17:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Z2B63U6FHNBVQ2Q7MW7R3YLCK5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-13T21:44:32Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"a0c34c78f01afd452fe47a60967a9d27bc1efc90fb6a1d15512e648d66ba693c","abstract_canon_sha256":"5186bb9e1ee40d32339beb197de6d3309142dc1ea654d10e8a036a5b41cf39fe"},"schema_version":"1.0"},"canonical_sha256":"ce83edd3c53b43586a1f65bf1de16257707315c836fb21b3f16f268653e45a4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:09.527819Z","signature_b64":"VjfbnpCkcXpBH1X4LUgf6VZjxlh3RWvH7Dx4EnuhjsVGPsj0BltaMX158TLuyKmy+xrHdNXvZAgG5FoJ9uZKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce83edd3c53b43586a1f65bf1de16257707315c836fb21b3f16f268653e45a4e","last_reissued_at":"2026-07-05T08:17:09.527366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:09.527366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08013","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":"2026-07-05T08:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CW8baAe+KLzh7/16QGD/Rhmm1CCsgFIsTrx7DPDacMLSNDURIPBLYAPsOZpl9ezcRSgVQF+m53HGzecdaPCWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:44.134609Z"},"content_sha256":"51ce114a26ce812fb4505c26fdc27e83b15ba731276d40b5661ccdba595c5466","schema_version":"1.0","event_id":"sha256:51ce114a26ce812fb4505c26fdc27e83b15ba731276d40b5661ccdba595c5466"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Z2B63U6FHNBVQ2Q7MW7R3YLCK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Alexander Tolmachev, Alexey Frolov, Anna Neopryatnaya, Ivan Butakov, Kirill Andreev, Sofia Malanchuk","submitted_at":"2023-05-13T21:44:32Z","abstract_excerpt":"The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking the dynamics of two mutual information (MI) values: between the hidden layer output and the DNN input/target. According to the hypothesis put forth by Shwartz-Ziv & Tishby (2017), the training process consists of two distinct phases: fitting and compression. The latter phase is believed to account for the good generalization performance exhibited by DNNs. Due to the challenging nature of estimating MI between high-di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08013","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/2305.08013/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":"2026-07-05T08:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xd4MVB9h1Rh+HNMS8W2TMdVY+19lqcbe7V0aqX2Xiq+0HLUH2g6zR3vVUO1rxajmmjAqSAQ4zvcPe+ZQphZ0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:44.135470Z"},"content_sha256":"bf29c4a770d953e3f1b115ba7f0e2973c285f16ec1c948e712cfbe7d67ceefd6","schema_version":"1.0","event_id":"sha256:bf29c4a770d953e3f1b115ba7f0e2973c285f16ec1c948e712cfbe7d67ceefd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5/bundle.json","state_url":"https://pith.science/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5/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":"2026-08-08T19:18:44Z","links":{"resolver":"https://pith.science/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5","bundle":"https://pith.science/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5/bundle.json","state":"https://pith.science/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2B63U6FHNBVQ2Q7MW7R3YLCK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z2B63U6FHNBVQ2Q7MW7R3YLCK5","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":"5186bb9e1ee40d32339beb197de6d3309142dc1ea654d10e8a036a5b41cf39fe","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-13T21:44:32Z","title_canon_sha256":"a0c34c78f01afd452fe47a60967a9d27bc1efc90fb6a1d15512e648d66ba693c"},"schema_version":"1.0","source":{"id":"2305.08013","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08013","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08013v2","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08013","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z2B63U6FHNBV","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z2B63U6FHNBVQ2Q7","created_at":"2026-07-05T08:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z2B63U6F","created_at":"2026-07-05T08:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:bf29c4a770d953e3f1b115ba7f0e2973c285f16ec1c948e712cfbe7d67ceefd6","target":"graph","created_at":"2026-07-05T08:17:09Z","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/2305.08013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking the dynamics of two mutual information (MI) values: between the hidden layer output and the DNN input/target. According to the hypothesis put forth by Shwartz-Ziv & Tishby (2017), the training process consists of two distinct phases: fitting and compression. The latter phase is believed to account for the good generalization performance exhibited by DNNs. Due to the challenging nature of estimating MI between high-di","authors_text":"Alexander Tolmachev, Alexey Frolov, Anna Neopryatnaya, Ivan Butakov, Kirill Andreev, Sofia Malanchuk","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-13T21:44:32Z","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08013","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":"sha256:51ce114a26ce812fb4505c26fdc27e83b15ba731276d40b5661ccdba595c5466","target":"record","created_at":"2026-07-05T08:17:09Z","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":"5186bb9e1ee40d32339beb197de6d3309142dc1ea654d10e8a036a5b41cf39fe","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-13T21:44:32Z","title_canon_sha256":"a0c34c78f01afd452fe47a60967a9d27bc1efc90fb6a1d15512e648d66ba693c"},"schema_version":"1.0","source":{"id":"2305.08013","kind":"arxiv","version":2}},"canonical_sha256":"ce83edd3c53b43586a1f65bf1de16257707315c836fb21b3f16f268653e45a4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce83edd3c53b43586a1f65bf1de16257707315c836fb21b3f16f268653e45a4e","first_computed_at":"2026-07-05T08:17:09.527366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:09.527366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VjfbnpCkcXpBH1X4LUgf6VZjxlh3RWvH7Dx4EnuhjsVGPsj0BltaMX158TLuyKmy+xrHdNXvZAgG5FoJ9uZKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:09.527819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08013","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51ce114a26ce812fb4505c26fdc27e83b15ba731276d40b5661ccdba595c5466","sha256:bf29c4a770d953e3f1b115ba7f0e2973c285f16ec1c948e712cfbe7d67ceefd6"],"state_sha256":"965e830aa8302a9c078dfe9c92c0c1c3cea4208f6ed251144bf5c3251b1d522b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sL3OeexjCp7VPPVFT+fFup0HapmDvmkuR4H5FRHQ5M+WsjgSsHmHNGSa8Xw0C7VG+QLYbJJNqeZix9fDzAPnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:18:44.156925Z","bundle_sha256":"6756923695118a2883ddafce6633bc6c5fe35182fb67c3b973319d2137b6e49e"}}