{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MKBKBSKUYGTKFWIYZNCFB57IXK","short_pith_number":"pith:MKBKBSKU","schema_version":"1.0","canonical_sha256":"6282a0c954c1a6a2d918cb4450f7e8baa8eaf4cff3a8e8be93a6a4a7ef6a1ba6","source":{"kind":"arxiv","id":"2607.22951","version":1},"attestation_state":"computed","paper":{"title":"Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Peter Popov, Robab Aghazadeh Chakherlou, Siddartha Khastgir, Xingyu Zhao","submitted_at":"2026-07-24T23:34:40Z","abstract_excerpt":"Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses under a specified operational profile. Conventional benchmark-based evaluation, often summarized by aggregate accuracy, provides a point estimate of performance but does not characterize the uncertainty associated with reliability claims. Currently, statistical inference methods for LLM reliability assessment are emerging. However, a key assumption underlying these models is that test outcomes can be treated as independent repeated trials. This assumption may be inap"},"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":"2607.22951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-24T23:34:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2eb88c6e8cc0306af439d8eb45ff76c8b920652e4b19ccacf3c1e869b255e3c","abstract_canon_sha256":"e1742e8e5f3513ea5647753eb284b45d549e7a90c2a780ca50fe7ff9781518ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:03.826912Z","signature_b64":"smebnxdBnhRvKmCgEM6FichKYXvjhKYJjrD21h7JJF5D+JruPFyrV9ytRSNeSmY5E82okyZYiLjDe7GO8oyEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6282a0c954c1a6a2d918cb4450f7e8baa8eaf4cff3a8e8be93a6a4a7ef6a1ba6","last_reissued_at":"2026-07-28T00:22:03.826138Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:03.826138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Peter Popov, Robab Aghazadeh Chakherlou, Siddartha Khastgir, Xingyu Zhao","submitted_at":"2026-07-24T23:34:40Z","abstract_excerpt":"Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses under a specified operational profile. Conventional benchmark-based evaluation, often summarized by aggregate accuracy, provides a point estimate of performance but does not characterize the uncertainty associated with reliability claims. Currently, statistical inference methods for LLM reliability assessment are emerging. However, a key assumption underlying these models is that test outcomes can be treated as independent repeated trials. This assumption may be inap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22951","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/2607.22951/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":"2607.22951","created_at":"2026-07-28T00:22:03.826577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22951v1","created_at":"2026-07-28T00:22:03.826577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22951","created_at":"2026-07-28T00:22:03.826577+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKBKBSKUYGTK","created_at":"2026-07-28T00:22:03.826577+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKBKBSKUYGTKFWIY","created_at":"2026-07-28T00:22:03.826577+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKBKBSKU","created_at":"2026-07-28T00:22:03.826577+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/MKBKBSKUYGTKFWIYZNCFB57IXK","json":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK.json","graph_json":"https://pith.science/api/pith-number/MKBKBSKUYGTKFWIYZNCFB57IXK/graph.json","events_json":"https://pith.science/api/pith-number/MKBKBSKUYGTKFWIYZNCFB57IXK/events.json","paper":"https://pith.science/paper/MKBKBSKU"},"agent_actions":{"view_html":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK","download_json":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK.json","view_paper":"https://pith.science/paper/MKBKBSKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22951&json=true","fetch_graph":"https://pith.science/api/pith-number/MKBKBSKUYGTKFWIYZNCFB57IXK/graph.json","fetch_events":"https://pith.science/api/pith-number/MKBKBSKUYGTKFWIYZNCFB57IXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK/action/storage_attestation","attest_author":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK/action/author_attestation","sign_citation":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK/action/citation_signature","submit_replication":"https://pith.science/pith/MKBKBSKUYGTKFWIYZNCFB57IXK/action/replication_record"}},"created_at":"2026-07-28T00:22:03.826577+00:00","updated_at":"2026-07-28T00:22:03.826577+00:00"}