{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YET7BKJN5SYWH5IVGA6273OPYM","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":"5f04b2dea2dbe6bcf24e095a57217b39311e6c94a2ae2fde8b12fd91b17754f7","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-27T19:04:49Z","title_canon_sha256":"08c992865a9377421ef490d3ec14b297c85501c88ec628c6b4c3aa51d24d20a6"},"schema_version":"1.0","source":{"id":"1712.09657","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09657","created_at":"2026-07-05T01:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09657v2","created_at":"2026-07-05T01:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09657","created_at":"2026-07-05T01:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"YET7BKJN5SYW","created_at":"2026-07-05T01:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"YET7BKJN5SYWH5IV","created_at":"2026-07-05T01:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"YET7BKJN","created_at":"2026-07-05T01:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:1e7c9c5a5e339156a7dea95e2070cf23d0aedcab8ba648d038c80ce19c41a10c","target":"graph","created_at":"2026-07-05T01:06:45Z","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/1712.09657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The information bottleneck (IB) approach to clustering takes a joint distribution $P\\!\\left(X,Y\\right)$ and maps the data $X$ to cluster labels $T$ which retain maximal information about $Y$ (Tishby et al., 1999). This objective results in an algorithm that clusters data points based upon the similarity of their conditional distributions $P\\!\\left(Y\\mid X\\right)$. This is in contrast to classic \"geometric clustering'' algorithms such as $k$-means and gaussian mixture models (GMMs) which take a set of observed data points $\\left\\{ \\mathbf{x}_{i}\\right\\} _{i=1:N}$ and cluster them based upon the","authors_text":"David J Schwab, DJ Strouse","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-27T19:04:49Z","title":"The information bottleneck and geometric clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09657","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":"sha256:44e87e2f1e8e6f59fbaf708c2450f05c32aa40e894160f2a9cd4c655ff277cad","target":"record","created_at":"2026-07-05T01:06:45Z","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":"5f04b2dea2dbe6bcf24e095a57217b39311e6c94a2ae2fde8b12fd91b17754f7","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-27T19:04:49Z","title_canon_sha256":"08c992865a9377421ef490d3ec14b297c85501c88ec628c6b4c3aa51d24d20a6"},"schema_version":"1.0","source":{"id":"1712.09657","kind":"arxiv","version":2}},"canonical_sha256":"c127f0a92decb163f515303dafedcfc3179c5096481f34012259cf9c16801281","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c127f0a92decb163f515303dafedcfc3179c5096481f34012259cf9c16801281","first_computed_at":"2026-07-05T01:06:45.833144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:06:45.833144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wpi1c4ZFzxj741iNqGCeywGEP98IeK1mpc/tolg7MuEV0IDbx7DATHUeU+5IvkBzmfMzlLW1cbHCfIIfK2RnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:06:45.833623Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.09657","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44e87e2f1e8e6f59fbaf708c2450f05c32aa40e894160f2a9cd4c655ff277cad","sha256:1e7c9c5a5e339156a7dea95e2070cf23d0aedcab8ba648d038c80ce19c41a10c"],"state_sha256":"4617c920039440b62ef08d0fe3a3bdb163ea22e0c1e58abf3f3d15e8de9f8193"}