{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YET7BKJN5SYWH5IVGA6273OPYM","short_pith_number":"pith:YET7BKJN","schema_version":"1.0","canonical_sha256":"c127f0a92decb163f515303dafedcfc3179c5096481f34012259cf9c16801281","source":{"kind":"arxiv","id":"1712.09657","version":2},"attestation_state":"computed","paper":{"title":"The information bottleneck and geometric clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"David J Schwab, DJ Strouse","submitted_at":"2017-12-27T19:04:49Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1712.09657","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-27T19:04:49Z","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"08c992865a9377421ef490d3ec14b297c85501c88ec628c6b4c3aa51d24d20a6","abstract_canon_sha256":"5f04b2dea2dbe6bcf24e095a57217b39311e6c94a2ae2fde8b12fd91b17754f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:45.833623Z","signature_b64":"Wpi1c4ZFzxj741iNqGCeywGEP98IeK1mpc/tolg7MuEV0IDbx7DATHUeU+5IvkBzmfMzlLW1cbHCfIIfK2RnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c127f0a92decb163f515303dafedcfc3179c5096481f34012259cf9c16801281","last_reissued_at":"2026-07-05T01:06:45.833144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:45.833144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The information bottleneck and geometric clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"David J Schwab, DJ Strouse","submitted_at":"2017-12-27T19:04:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09657","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/1712.09657/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.09657","created_at":"2026-07-05T01:06:45.833196+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09657v2","created_at":"2026-07-05T01:06:45.833196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09657","created_at":"2026-07-05T01:06:45.833196+00:00"},{"alias_kind":"pith_short_12","alias_value":"YET7BKJN5SYW","created_at":"2026-07-05T01:06:45.833196+00:00"},{"alias_kind":"pith_short_16","alias_value":"YET7BKJN5SYWH5IV","created_at":"2026-07-05T01:06:45.833196+00:00"},{"alias_kind":"pith_short_8","alias_value":"YET7BKJN","created_at":"2026-07-05T01:06:45.833196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03533","citing_title":"Topic Identification in LLM Input-Output Pairs through the Lens of Information Bottleneck","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM","json":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM.json","graph_json":"https://pith.science/api/pith-number/YET7BKJN5SYWH5IVGA6273OPYM/graph.json","events_json":"https://pith.science/api/pith-number/YET7BKJN5SYWH5IVGA6273OPYM/events.json","paper":"https://pith.science/paper/YET7BKJN"},"agent_actions":{"view_html":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM","download_json":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM.json","view_paper":"https://pith.science/paper/YET7BKJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09657&json=true","fetch_graph":"https://pith.science/api/pith-number/YET7BKJN5SYWH5IVGA6273OPYM/graph.json","fetch_events":"https://pith.science/api/pith-number/YET7BKJN5SYWH5IVGA6273OPYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM/action/storage_attestation","attest_author":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM/action/author_attestation","sign_citation":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM/action/citation_signature","submit_replication":"https://pith.science/pith/YET7BKJN5SYWH5IVGA6273OPYM/action/replication_record"}},"created_at":"2026-07-05T01:06:45.833196+00:00","updated_at":"2026-07-05T01:06:45.833196+00:00"}