{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2BSWEUERZO6RSF74QZJLLBNV5P","short_pith_number":"pith:2BSWEUER","schema_version":"1.0","canonical_sha256":"d065625091cbbd1917fc8652b585b5ebffb53402ccb3ce0d974ee73dabd84ffe","source":{"kind":"arxiv","id":"2508.21762","version":4},"attestation_state":"computed","paper":{"title":"Reasoning-Intensive Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diane Tchuindjo, Omar Khattab","submitted_at":"2025-08-29T16:37:42Z","abstract_excerpt":"AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducing subtle numerical scores from text. Unlike standard language regression tasks such as sentiment or similarity analysis, RiR often appears instead in ad-hoc applications such as rubric-based scoring, modeling dense rewards in complex environments, or domain-specific retrieval, where much deeper analysis of context is required while only limited task-specific training data and computation are available. We cast four realistic problems as RiR tasks t"},"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":"2508.21762","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T16:37:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f05bf2a1e623672d8270279b401380b8af0076ece991b947bb8e359580c87c9b","abstract_canon_sha256":"7a331287be74db049c5c392a873cc5bcc854bbd6b2028bb7cb7e48e620c88e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:19.867230Z","signature_b64":"DD5/A7oBsGOe8VuKDKMGbssnivMVX1medOP2xb+JBl/vUcJT/BwhTPLW3Bdr5s17tn29Ijz5C9MUvjaxeuKvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d065625091cbbd1917fc8652b585b5ebffb53402ccb3ce0d974ee73dabd84ffe","last_reissued_at":"2026-06-01T01:02:19.866338Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:19.866338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning-Intensive Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diane Tchuindjo, Omar Khattab","submitted_at":"2025-08-29T16:37:42Z","abstract_excerpt":"AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducing subtle numerical scores from text. Unlike standard language regression tasks such as sentiment or similarity analysis, RiR often appears instead in ad-hoc applications such as rubric-based scoring, modeling dense rewards in complex environments, or domain-specific retrieval, where much deeper analysis of context is required while only limited task-specific training data and computation are available. We cast four realistic problems as RiR tasks t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MENTAT achieves up to 65% improvement over both prompting frozen LLMs and fine-tuning Transformer encoders on four realistic reasoning-intensive regression tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The four problems cast as RiR tasks are representative of the broader class of reasoning-intensive regression problems and the reported gains are not specific to the chosen benchmarks or evaluation protocol.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MENTAT improves performance on reasoning-intensive regression tasks by up to 65% over standard LLM prompting and encoder fine-tuning by combining batch prompt optimization with neural ensembles.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2aca125d6226a21a82968dec25e5fe8378af88398fb81ec8472001fe54827726"},"source":{"id":"2508.21762","kind":"arxiv","version":4},"verdict":{"id":"3b2342f4-6234-4e50-9595-0dd74919429f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T20:12:44.900780Z","strongest_claim":"MENTAT achieves up to 65% improvement over both prompting frozen LLMs and fine-tuning Transformer encoders on four realistic reasoning-intensive regression tasks.","one_line_summary":"MENTAT improves performance on reasoning-intensive regression tasks by up to 65% over standard LLM prompting and encoder fine-tuning by combining batch prompt optimization with neural ensembles.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The four problems cast as RiR tasks are representative of the broader class of reasoning-intensive regression problems and the reported gains are not specific to the chosen benchmarks or evaluation protocol.","pith_extraction_headline":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.21762/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":"2508.21762","created_at":"2026-06-01T01:02:19.866498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21762v4","created_at":"2026-06-01T01:02:19.866498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21762","created_at":"2026-06-01T01:02:19.866498+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BSWEUERZO6R","created_at":"2026-06-01T01:02:19.866498+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BSWEUERZO6RSF74","created_at":"2026-06-01T01:02:19.866498+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BSWEUER","created_at":"2026-06-01T01:02:19.866498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20740","citing_title":"Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P","json":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P.json","graph_json":"https://pith.science/api/pith-number/2BSWEUERZO6RSF74QZJLLBNV5P/graph.json","events_json":"https://pith.science/api/pith-number/2BSWEUERZO6RSF74QZJLLBNV5P/events.json","paper":"https://pith.science/paper/2BSWEUER"},"agent_actions":{"view_html":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P","download_json":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P.json","view_paper":"https://pith.science/paper/2BSWEUER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21762&json=true","fetch_graph":"https://pith.science/api/pith-number/2BSWEUERZO6RSF74QZJLLBNV5P/graph.json","fetch_events":"https://pith.science/api/pith-number/2BSWEUERZO6RSF74QZJLLBNV5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P/action/storage_attestation","attest_author":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P/action/author_attestation","sign_citation":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P/action/citation_signature","submit_replication":"https://pith.science/pith/2BSWEUERZO6RSF74QZJLLBNV5P/action/replication_record"}},"created_at":"2026-06-01T01:02:19.866498+00:00","updated_at":"2026-06-01T01:02:19.866498+00:00"}