{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DAJCCRFGBEB6GHPSSMTXRA6HJ7","short_pith_number":"pith:DAJCCRFG","schema_version":"1.0","canonical_sha256":"18122144a60903e31df293277883c74fcfd8f22953657cc66fd748aff64da305","source":{"kind":"arxiv","id":"2509.03533","version":1},"attestation_state":"computed","paper":{"title":"Topic Identification in LLM Input-Output Pairs through the Lens of Information Bottleneck","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","q-fin.GN"],"primary_cat":"cs.CL","authors_text":"Igor Halperin","submitted_at":"2025-08-26T20:00:51Z","abstract_excerpt":"Large Language Models (LLMs) are prone to critical failure modes, including \\textit{intrinsic faithfulness hallucinations} (also known as confabulations), where a response deviates semantically from the provided context. Frameworks designed to detect this, such as Semantic Divergence Metrics (SDM), rely on identifying latent topics shared between prompts and responses, typically by applying geometric clustering to their sentence embeddings. This creates a disconnect, as the topics are optimized for spatial proximity, not for the downstream information-theoretic analysis. In this paper, we brid"},"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":"2509.03533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T20:00:51Z","cross_cats_sorted":["cs.LG","q-fin.GN"],"title_canon_sha256":"ea00599de9e3e35556a74d7cda5a419dab3db5d9781be119c974f2a416e565b8","abstract_canon_sha256":"e0d5a3540de8336dda4f6f535dab9e0e5767eb77e8cc6b58ed40a0c9f4fea2f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:41.718430Z","signature_b64":"RY1dxQOPtha3MadhD9c7+X1WBhWHT/ZRciAh6trGukxdkg60J2+UlUSV8zhoPXtEgbhpbR8wVsbNelRlz5Y3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18122144a60903e31df293277883c74fcfd8f22953657cc66fd748aff64da305","last_reissued_at":"2026-07-05T12:04:41.717839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:41.717839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Identification in LLM Input-Output Pairs through the Lens of Information Bottleneck","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","q-fin.GN"],"primary_cat":"cs.CL","authors_text":"Igor Halperin","submitted_at":"2025-08-26T20:00:51Z","abstract_excerpt":"Large Language Models (LLMs) are prone to critical failure modes, including \\textit{intrinsic faithfulness hallucinations} (also known as confabulations), where a response deviates semantically from the provided context. Frameworks designed to detect this, such as Semantic Divergence Metrics (SDM), rely on identifying latent topics shared between prompts and responses, typically by applying geometric clustering to their sentence embeddings. This creates a disconnect, as the topics are optimized for spatial proximity, not for the downstream information-theoretic analysis. In this paper, we brid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03533","kind":"arxiv","version":1},"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/2509.03533/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":"2509.03533","created_at":"2026-07-05T12:04:41.717898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03533v1","created_at":"2026-07-05T12:04:41.717898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03533","created_at":"2026-07-05T12:04:41.717898+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAJCCRFGBEB6","created_at":"2026-07-05T12:04:41.717898+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAJCCRFGBEB6GHPS","created_at":"2026-07-05T12:04:41.717898+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAJCCRFG","created_at":"2026-07-05T12:04:41.717898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7","json":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7.json","graph_json":"https://pith.science/api/pith-number/DAJCCRFGBEB6GHPSSMTXRA6HJ7/graph.json","events_json":"https://pith.science/api/pith-number/DAJCCRFGBEB6GHPSSMTXRA6HJ7/events.json","paper":"https://pith.science/paper/DAJCCRFG"},"agent_actions":{"view_html":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7","download_json":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7.json","view_paper":"https://pith.science/paper/DAJCCRFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03533&json=true","fetch_graph":"https://pith.science/api/pith-number/DAJCCRFGBEB6GHPSSMTXRA6HJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/DAJCCRFGBEB6GHPSSMTXRA6HJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7/action/storage_attestation","attest_author":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7/action/author_attestation","sign_citation":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7/action/citation_signature","submit_replication":"https://pith.science/pith/DAJCCRFGBEB6GHPSSMTXRA6HJ7/action/replication_record"}},"created_at":"2026-07-05T12:04:41.717898+00:00","updated_at":"2026-07-05T12:04:41.717898+00:00"}