{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:COUQ6OIQ2YDCWRXVHSUW35EZKS","short_pith_number":"pith:COUQ6OIQ","canonical_record":{"source":{"id":"2602.00906","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T21:18:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DS","cs.IT","math.IT"],"title_canon_sha256":"09c1a2f0b896d2323af97c5dfd4a990494b8d768f3a2d1265f5a5f067db8c74b","abstract_canon_sha256":"ded0d6a9ce377f077ab0fd83b96766f8267820895964baf8db5a43b51069eaf6"},"schema_version":"1.0"},"canonical_sha256":"13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd","source":{"kind":"arxiv","id":"2602.00906","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:COUQ6OIQ2YDCWRXVHSUW35EZKS","target":"record","payload":{"canonical_record":{"source":{"id":"2602.00906","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T21:18:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DS","cs.IT","math.IT"],"title_canon_sha256":"09c1a2f0b896d2323af97c5dfd4a990494b8d768f3a2d1265f5a5f067db8c74b","abstract_canon_sha256":"ded0d6a9ce377f077ab0fd83b96766f8267820895964baf8db5a43b51069eaf6"},"schema_version":"1.0"},"canonical_sha256":"13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:41.728035Z","signature_b64":"TIh+AGQvzPmAjOZV7Jgi8PzphEPCqqRherNOjfz0IlX+mPoT9FbJD9oO9ozuFj5FsX3qEkZAxjzV1/ZK1+0MBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13a90f3910d6062b46f53ca96df49954b8fd9a643c7b6c3a10203f560440d1fd","last_reissued_at":"2026-06-02T01:03:41.727527Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:41.727527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.00906","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGBCxIjO8FIbloYhnKcnf1TdsX9D0EqkDWEO5MKWP9zuQDFo0BVPwx7E2PQXL8y1UgF99AWJSpm/qz9ddMq5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:14:11.571673Z"},"content_sha256":"b6f57f01c81739ff7446bef163ed25f7acb27176ba32c156fec625d914b528d5","schema_version":"1.0","event_id":"sha256:b6f57f01c81739ff7446bef163ed25f7acb27176ba32c156fec625d914b528d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:COUQ6OIQ2YDCWRXVHSUW35EZKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts","cross_cats":["cs.AI","cs.CL","cs.DS","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Anxin Guo, Jingwei Li","submitted_at":"2026-01-31T21:18:28Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"38afcfcfca17f0f53a74524565a3b575ad1a7c2b5c079ea23961b78a198b077c"},"source":{"id":"2602.00906","kind":"arxiv","version":7},"verdict":{"id":"d95c20da-8cad-440e-93ee-c14efa3fcfd6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:33:35.435664Z","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.","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","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.","pith_extraction_headline":"Even with perfect data and training, limited capacity forces LLMs to assign high confidence to some non-facts"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.00906/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":2,"snapshot_sha256":"076041c912f00d4f04be6d3068f4d74b681878e687840297e73be32065210925"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d95c20da-8cad-440e-93ee-c14efa3fcfd6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SzpI2iJJD0i9OO3pmUQ60LZFOwMK38+3YF6QBwc1hh53X46qv35scyA2wIdGbU83IXMyHknxW9bNliovptJEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:14:11.581146Z"},"content_sha256":"48bcfec07a2305fc9e613eb81701edfe88c5ca09daab464a3dce49a95b67822c","schema_version":"1.0","event_id":"sha256:48bcfec07a2305fc9e613eb81701edfe88c5ca09daab464a3dce49a95b67822c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS/bundle.json","state_url":"https://pith.science/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS/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":"2026-08-10T19:14:11Z","links":{"resolver":"https://pith.science/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS","bundle":"https://pith.science/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS/bundle.json","state":"https://pith.science/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/COUQ6OIQ2YDCWRXVHSUW35EZKS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nCBY6qmcd18GJUZl+Q2SbwRPv9pUdb9o8A2Cn0S0dd1dQrnLif0lZXgXFgDVOux5FlIFQXfR7V3EP943NhIUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:14:11.591862Z","bundle_sha256":"7a44896c8713b294f67eba775fde8dd173044101aea531a6679a02ef2d920e85"}}