{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:26D3XP3DLP2H344YYWHNTPSQIJ","short_pith_number":"pith:26D3XP3D","schema_version":"1.0","canonical_sha256":"d787bbbf635bf47df398c58ed9be50427a89126b24b7ece5e5d3d0c6ffb7f46e","source":{"kind":"arxiv","id":"2605.30981","version":1},"attestation_state":"computed","paper":{"title":"Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amit Sheth, Atishay Jain, Michael Stewart, Riju Marwah, Ritvik Garimella, Vishal Pallagani","submitted_at":"2026-05-29T08:18:23Z","abstract_excerpt":"Autoregressive language models frequently degrade during long-horizon generation, producing repetitive text, losing instruction adherence, and exhibiting unstable entropy. Despite the prevalence of these failures, practitioners lack online diagnostics to detect them in real-time as they occur. We formalize this degradation as cognitive fatigue, a measurable generation-time state characterized by decay in attention to the original prompt, representational drift, and entropy miscalibration. We introduce the Fatigue Index (FI), a lightweight, model-agnostic diagnostic that aggregates these three "},"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":"2605.30981","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T08:18:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1088fdde49ab4620853c63d0651a430f732b32badefeb7d04d3522780488c005","abstract_canon_sha256":"795e03f895a85b4b65e55fc07dbecea244187c733be134d77cb010fe0dd311cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:28.481956Z","signature_b64":"zke0SVF/FFUbBngIjdthDQWYuon3/wge7PcslLM8jdL5JZUWrkUYA+iLUhP97auE7TxOLFZb+VXSo41CNjCICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d787bbbf635bf47df398c58ed9be50427a89126b24b7ece5e5d3d0c6ffb7f46e","last_reissued_at":"2026-06-01T01:03:28.480983Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:28.480983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amit Sheth, Atishay Jain, Michael Stewart, Riju Marwah, Ritvik Garimella, Vishal Pallagani","submitted_at":"2026-05-29T08:18:23Z","abstract_excerpt":"Autoregressive language models frequently degrade during long-horizon generation, producing repetitive text, losing instruction adherence, and exhibiting unstable entropy. Despite the prevalence of these failures, practitioners lack online diagnostics to detect them in real-time as they occur. We formalize this degradation as cognitive fatigue, a measurable generation-time state characterized by decay in attention to the original prompt, representational drift, and entropy miscalibration. We introduce the Fatigue Index (FI), a lightweight, model-agnostic diagnostic that aggregates these three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30981","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/2605.30981/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":"2605.30981","created_at":"2026-06-01T01:03:28.481124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30981v1","created_at":"2026-06-01T01:03:28.481124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30981","created_at":"2026-06-01T01:03:28.481124+00:00"},{"alias_kind":"pith_short_12","alias_value":"26D3XP3DLP2H","created_at":"2026-06-01T01:03:28.481124+00:00"},{"alias_kind":"pith_short_16","alias_value":"26D3XP3DLP2H344Y","created_at":"2026-06-01T01:03:28.481124+00:00"},{"alias_kind":"pith_short_8","alias_value":"26D3XP3D","created_at":"2026-06-01T01:03:28.481124+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/26D3XP3DLP2H344YYWHNTPSQIJ","json":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ.json","graph_json":"https://pith.science/api/pith-number/26D3XP3DLP2H344YYWHNTPSQIJ/graph.json","events_json":"https://pith.science/api/pith-number/26D3XP3DLP2H344YYWHNTPSQIJ/events.json","paper":"https://pith.science/paper/26D3XP3D"},"agent_actions":{"view_html":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ","download_json":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ.json","view_paper":"https://pith.science/paper/26D3XP3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30981&json=true","fetch_graph":"https://pith.science/api/pith-number/26D3XP3DLP2H344YYWHNTPSQIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/26D3XP3DLP2H344YYWHNTPSQIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ/action/storage_attestation","attest_author":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ/action/author_attestation","sign_citation":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ/action/citation_signature","submit_replication":"https://pith.science/pith/26D3XP3DLP2H344YYWHNTPSQIJ/action/replication_record"}},"created_at":"2026-06-01T01:03:28.481124+00:00","updated_at":"2026-06-01T01:03:28.481124+00:00"}