{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K4D5DVC7LTTIW5TLMQRB3F7PFJ","short_pith_number":"pith:K4D5DVC7","schema_version":"1.0","canonical_sha256":"5707d1d45f5ce68b766b64221d97ef2a4f0221265587b201df06c06bb72033c2","source":{"kind":"arxiv","id":"2601.09001","version":4},"attestation_state":"computed","paper":{"title":"Entropy Sentinel: Continuous LLM Accuracy Monitoring from Decoding Entropy Traces in STEM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luciano Del Corro, Pedro Memoli Buffa","submitted_at":"2026-01-13T21:54:38Z","abstract_excerpt":"Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improvement--prioritizing data acquisition to close the largest performance gaps. We test whether an inference-time signal can estimate slice-level accuracy under domain shift. For each response, we compute an output-entropy profile from final-layer next-token probabilities (from top-$k$ logprobs) and summarize it with different statistics. A lightweight classifier predicts instance correctness, and averaging predicted probabilities yields a domain-level ac"},"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":"2601.09001","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-13T21:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"aac40efc5814a9e197fdc60acd3047beb63a7b36f52ea05347e3dd77ef1f01d2","abstract_canon_sha256":"2306a55281ec55297401b1b0ec2d5934193d82f2a539a4118a24bb4d2c4c40c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:54.964170Z","signature_b64":"bU74XTAHK14brQ+629qrlNKLChaD2x8dSoVSODfDNTUi22Vmin7ewbZZXKUWJ991sg2DFsE5pr3fU+wxg0WTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5707d1d45f5ce68b766b64221d97ef2a4f0221265587b201df06c06bb72033c2","last_reissued_at":"2026-05-27T01:04:54.963237Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:54.963237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy Sentinel: Continuous LLM Accuracy Monitoring from Decoding Entropy Traces in STEM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luciano Del Corro, Pedro Memoli Buffa","submitted_at":"2026-01-13T21:54:38Z","abstract_excerpt":"Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improvement--prioritizing data acquisition to close the largest performance gaps. We test whether an inference-time signal can estimate slice-level accuracy under domain shift. For each response, we compute an output-entropy profile from final-layer next-token probabilities (from top-$k$ logprobs) and summarize it with different statistics. A lightweight classifier predicts instance correctness, and averaging predicted probabilities yields a domain-level ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09001","kind":"arxiv","version":4},"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/2601.09001/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":"2601.09001","created_at":"2026-05-27T01:04:54.963368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.09001v4","created_at":"2026-05-27T01:04:54.963368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09001","created_at":"2026-05-27T01:04:54.963368+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4D5DVC7LTTI","created_at":"2026-05-27T01:04:54.963368+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4D5DVC7LTTIW5TL","created_at":"2026-05-27T01:04:54.963368+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4D5DVC7","created_at":"2026-05-27T01:04:54.963368+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/K4D5DVC7LTTIW5TLMQRB3F7PFJ","json":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ.json","graph_json":"https://pith.science/api/pith-number/K4D5DVC7LTTIW5TLMQRB3F7PFJ/graph.json","events_json":"https://pith.science/api/pith-number/K4D5DVC7LTTIW5TLMQRB3F7PFJ/events.json","paper":"https://pith.science/paper/K4D5DVC7"},"agent_actions":{"view_html":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ","download_json":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ.json","view_paper":"https://pith.science/paper/K4D5DVC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.09001&json=true","fetch_graph":"https://pith.science/api/pith-number/K4D5DVC7LTTIW5TLMQRB3F7PFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/K4D5DVC7LTTIW5TLMQRB3F7PFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ/action/storage_attestation","attest_author":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ/action/author_attestation","sign_citation":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ/action/citation_signature","submit_replication":"https://pith.science/pith/K4D5DVC7LTTIW5TLMQRB3F7PFJ/action/replication_record"}},"created_at":"2026-05-27T01:04:54.963368+00:00","updated_at":"2026-05-27T01:04:54.963368+00:00"}