{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:COUQ6OIQ2YDCWRXVHSUW35EZKS","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":"ded0d6a9ce377f077ab0fd83b96766f8267820895964baf8db5a43b51069eaf6","cross_cats_sorted":["cs.AI","cs.CL","cs.DS","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T21:18:28Z","title_canon_sha256":"09c1a2f0b896d2323af97c5dfd4a990494b8d768f3a2d1265f5a5f067db8c74b"},"schema_version":"1.0","source":{"id":"2602.00906","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.00906","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.00906v7","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00906","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"COUQ6OIQ2YDC","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"COUQ6OIQ2YDCWRXV","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"COUQ6OIQ","created_at":"2026-06-02T01:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:48bcfec07a2305fc9e613eb81701edfe88c5ca09daab464a3dce49a95b67822c","target":"graph","created_at":"2026-06-02T01:03:41Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"even with optimal training, perfect data, and a simplified closed world setting, the information-theoretically optimal strategy under limited capacity is not to abstain or forget, but to assign high confidence to some non-facts, resulting in hallucination."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The regime in which facts are sparse in the universe of plausible claims, together with the modeling choice that unifies discrete Bloom-filter error with continuous log-loss under a single rate-distortion objective."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Hallucinations are the space-optimal behavior for limited-capacity models performing membership testing on sparse facts, as shown by a rate-distortion theorem that equates optimal memory use to minimum KL divergence between fact and non-fact score distributions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts"}],"snapshot_sha256":"38afcfcfca17f0f53a74524565a3b575ad1a7c2b5c079ea23961b78a198b077c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"076041c912f00d4f04be6d3068f4d74b681878e687840297e73be32065210925"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.00906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models often hallucinate with high confidence on \"random facts\" that lack inferable patterns. We formalize the memorization of such facts as a membership testing problem, unifying the discrete error metrics of Bloom filters with the continuous log-loss of LLMs. By analyzing this problem in the regime where facts are sparse in the universe of plausible claims, we establish a rate-distortion theorem: the optimal memory efficiency is characterized by the minimum KL divergence between score distributions on facts and non-facts. This theoretical framework provides a distinctive expla","authors_text":"Anxin Guo, Jingwei Li","cross_cats":["cs.AI","cs.CL","cs.DS","cs.IT","math.IT"],"headline":"Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T21:18:28Z","title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00906","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-16T08:33:35.435664Z","id":"d95c20da-8cad-440e-93ee-c14efa3fcfd6","model_set":{"reader":"grok-4.3"},"one_line_summary":"Hallucinations are the space-optimal behavior for limited-capacity models performing membership testing on sparse facts, as shown by a rate-distortion theorem that equates optimal memory use to minimum KL divergence between fact and non-fact score distributions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts","strongest_claim":"even with optimal training, perfect data, and a simplified closed world setting, the information-theoretically optimal strategy under limited capacity is not to abstain or forget, but to assign high confidence to some non-facts, resulting in hallucination.","weakest_assumption":"The regime in which facts are sparse in the universe of plausible claims, together with the modeling choice that unifies discrete Bloom-filter error with continuous log-loss under a single rate-distortion objective."}},"verdict_id":"d95c20da-8cad-440e-93ee-c14efa3fcfd6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b6f57f01c81739ff7446bef163ed25f7acb27176ba32c156fec625d914b528d5","target":"record","created_at":"2026-06-02T01:03:41Z","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":"ded0d6a9ce377f077ab0fd83b96766f8267820895964baf8db5a43b51069eaf6","cross_cats_sorted":["cs.AI","cs.CL","cs.DS","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T21:18:28Z","title_canon_sha256":"09c1a2f0b896d2323af97c5dfd4a990494b8d768f3a2d1265f5a5f067db8c74b"},"schema_version":"1.0","source":{"id":"2602.00906","kind":"arxiv","version":7}},"canonical_sha256":"13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd","first_computed_at":"2026-06-02T01:03:41.727527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:41.727527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TIh+AGQvzPmAjOZV7Jgi8PzphEPCqqRherNOjfz0IlX+mPoT9FbJD9oO9ozuFj5FsX3qEkZAxjzV1/ZK1+0MBg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:41.728035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.00906","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f57f01c81739ff7446bef163ed25f7acb27176ba32c156fec625d914b528d5","sha256:48bcfec07a2305fc9e613eb81701edfe88c5ca09daab464a3dce49a95b67822c"],"state_sha256":"204c629900663f6c0591d91c01f8b8925458e9198f1cb18c226b7d4572878dd3"}