{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:SDDFNYUJ4NFDYJ6YBNBDAHFK5C","short_pith_number":"pith:SDDFNYUJ","canonical_record":{"source":{"id":"1605.07332","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-24T08:16:54Z","cross_cats_sorted":[],"title_canon_sha256":"1a9e5b361456c7f9dc8c3ba5bd57fac9768db34afe56cdb659105b12429fcd82","abstract_canon_sha256":"2500320dc0e6b38c9f04a1604228793e387119f2bb9eb9f407a12d9d97e07fd7"},"schema_version":"1.0"},"canonical_sha256":"90c656e289e34a3c27d80b42301caae89da62151d99cb8737f04878793f673db","source":{"kind":"arxiv","id":"1605.07332","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07332","created_at":"2026-05-18T01:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07332v2","created_at":"2026-05-18T01:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07332","created_at":"2026-05-18T01:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"SDDFNYUJ4NFD","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SDDFNYUJ4NFDYJ6Y","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SDDFNYUJ","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:SDDFNYUJ4NFDYJ6YBNBDAHFK5C","target":"record","payload":{"canonical_record":{"source":{"id":"1605.07332","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-24T08:16:54Z","cross_cats_sorted":[],"title_canon_sha256":"1a9e5b361456c7f9dc8c3ba5bd57fac9768db34afe56cdb659105b12429fcd82","abstract_canon_sha256":"2500320dc0e6b38c9f04a1604228793e387119f2bb9eb9f407a12d9d97e07fd7"},"schema_version":"1.0"},"canonical_sha256":"90c656e289e34a3c27d80b42301caae89da62151d99cb8737f04878793f673db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:15.649556Z","signature_b64":"gxxjkKuYfxcqa2zzBd9f0vBWIRtA6e4HjW3yUGCVbATfvoYsHrhutEALXDkdF8QnTLYRA5D5lVlS5mgBKw19Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90c656e289e34a3c27d80b42301caae89da62151d99cb8737f04878793f673db","last_reissued_at":"2026-05-18T01:01:15.648880Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:15.648880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.07332","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":"2026-05-18T01:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBTYxbozYZrQsxdHQCSSPiaiU0H+PBAfgAxuqG20UsV7jxaZ4kGlDuiuJDXux+b76PgBdZhAwDmmQ52keJ5CCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T03:48:17.827536Z"},"content_sha256":"1f31c6bfeb45c4fd1e1029920b263f6867b0c854a822414996d7437b39ad5909","schema_version":"1.0","event_id":"sha256:1f31c6bfeb45c4fd1e1029920b263f6867b0c854a822414996d7437b39ad5909"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:SDDFNYUJ4NFDYJ6YBNBDAHFK5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relevant sparse codes with variational information bottleneck","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Gasper Tkacik, Matthew Chalk, Olivier Marre","submitted_at":"2016-05-24T08:16:54Z","abstract_excerpt":"In many applications, it is desirable to extract only the relevant aspects of data. A principled way to do this is the information bottleneck (IB) method, where one seeks a code that maximizes information about a 'relevance' variable, Y, while constraining the information encoded about the original data, X. Unfortunately however, the IB method is computationally demanding when data are high-dimensional and/or non-gaussian. Here we propose an approximate variational scheme for maximizing a lower bound on the IB objective, analogous to variational EM. Using this method, we derive an IB algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07332","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":""},"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":"2026-05-18T01:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMhUKDejT/By1H7iZI+xCqf+3ZJucuXerubNpFVDpuwdkI5i2JUJgxwAnqnA/0q/62f6s/tVuhSPMZ/WJctiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T03:48:17.827869Z"},"content_sha256":"570126cc6f8a702154db06d9df205511787b6a5f3eabc7b1cb95d59048b9ebda","schema_version":"1.0","event_id":"sha256:570126cc6f8a702154db06d9df205511787b6a5f3eabc7b1cb95d59048b9ebda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C/bundle.json","state_url":"https://pith.science/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C/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":"2026-06-21T03:48:17Z","links":{"resolver":"https://pith.science/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C","bundle":"https://pith.science/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C/bundle.json","state":"https://pith.science/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDDFNYUJ4NFDYJ6YBNBDAHFK5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:SDDFNYUJ4NFDYJ6YBNBDAHFK5C","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":"2500320dc0e6b38c9f04a1604228793e387119f2bb9eb9f407a12d9d97e07fd7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-24T08:16:54Z","title_canon_sha256":"1a9e5b361456c7f9dc8c3ba5bd57fac9768db34afe56cdb659105b12429fcd82"},"schema_version":"1.0","source":{"id":"1605.07332","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07332","created_at":"2026-05-18T01:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07332v2","created_at":"2026-05-18T01:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07332","created_at":"2026-05-18T01:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"SDDFNYUJ4NFD","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SDDFNYUJ4NFDYJ6Y","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SDDFNYUJ","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:570126cc6f8a702154db06d9df205511787b6a5f3eabc7b1cb95d59048b9ebda","target":"graph","created_at":"2026-05-18T01:01:15Z","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"},"paper":{"abstract_excerpt":"In many applications, it is desirable to extract only the relevant aspects of data. A principled way to do this is the information bottleneck (IB) method, where one seeks a code that maximizes information about a 'relevance' variable, Y, while constraining the information encoded about the original data, X. Unfortunately however, the IB method is computationally demanding when data are high-dimensional and/or non-gaussian. Here we propose an approximate variational scheme for maximizing a lower bound on the IB objective, analogous to variational EM. Using this method, we derive an IB algorithm","authors_text":"Gasper Tkacik, Matthew Chalk, Olivier Marre","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-24T08:16:54Z","title":"Relevant sparse codes with variational information bottleneck"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07332","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":"sha256:1f31c6bfeb45c4fd1e1029920b263f6867b0c854a822414996d7437b39ad5909","target":"record","created_at":"2026-05-18T01:01:15Z","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":"2500320dc0e6b38c9f04a1604228793e387119f2bb9eb9f407a12d9d97e07fd7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-24T08:16:54Z","title_canon_sha256":"1a9e5b361456c7f9dc8c3ba5bd57fac9768db34afe56cdb659105b12429fcd82"},"schema_version":"1.0","source":{"id":"1605.07332","kind":"arxiv","version":2}},"canonical_sha256":"90c656e289e34a3c27d80b42301caae89da62151d99cb8737f04878793f673db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90c656e289e34a3c27d80b42301caae89da62151d99cb8737f04878793f673db","first_computed_at":"2026-05-18T01:01:15.648880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:01:15.648880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxxjkKuYfxcqa2zzBd9f0vBWIRtA6e4HjW3yUGCVbATfvoYsHrhutEALXDkdF8QnTLYRA5D5lVlS5mgBKw19Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:01:15.649556Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.07332","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f31c6bfeb45c4fd1e1029920b263f6867b0c854a822414996d7437b39ad5909","sha256:570126cc6f8a702154db06d9df205511787b6a5f3eabc7b1cb95d59048b9ebda"],"state_sha256":"8a04f3675f58cc96833238b46c48693fe749037a097295be0e215457febba83c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSlOpYStMmLm5BDGgUyMkbhPKChYCJ+8esHT39fu5h3zKp7BgmuNWRp+MquWBgkfWfZtFNojOnJYVsHxmYRmCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-21T03:48:17.829772Z","bundle_sha256":"9feb8bef0702f525e5277b039fcc3cdfd77c37a901cb77dcc1017c637dc7a51f"}}