{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2BSWEUERZO6RSF74QZJLLBNV5P","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":"7a331287be74db049c5c392a873cc5bcc854bbd6b2028bb7cb7e48e620c88e73","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T16:37:42Z","title_canon_sha256":"f05bf2a1e623672d8270279b401380b8af0076ece991b947bb8e359580c87c9b"},"schema_version":"1.0","source":{"id":"2508.21762","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21762","created_at":"2026-06-01T01:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21762v4","created_at":"2026-06-01T01:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21762","created_at":"2026-06-01T01:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"2BSWEUERZO6R","created_at":"2026-06-01T01:02:19Z"},{"alias_kind":"pith_short_16","alias_value":"2BSWEUERZO6RSF74","created_at":"2026-06-01T01:02:19Z"},{"alias_kind":"pith_short_8","alias_value":"2BSWEUER","created_at":"2026-06-01T01:02:19Z"}],"graph_snapshots":[{"event_id":"sha256:fd58ab43aecabd6b6d417d6d2508713d83918426f9a360195ad6b7a868446e5c","target":"graph","created_at":"2026-06-01T01:02:19Z","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":"MENTAT achieves up to 65% improvement over both prompting frozen LLMs and fine-tuning Transformer encoders on four realistic reasoning-intensive regression tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning."}],"snapshot_sha256":"2aca125d6226a21a82968dec25e5fe8378af88398fb81ec8472001fe54827726"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.21762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Diane Tchuindjo, Omar Khattab","cross_cats":["cs.AI"],"headline":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T16:37:42Z","title":"Reasoning-Intensive Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21762","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-18T20:12:44.900780Z","id":"3b2342f4-6234-4e50-9595-0dd74919429f","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"MENTAT improves reasoning-intensive regression by up to 65 percent over frozen LLM prompting and encoder fine-tuning.","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.","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."}},"verdict_id":"3b2342f4-6234-4e50-9595-0dd74919429f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:27f3e5d4e648c4b52691bc8fb88e79af60563a48953a66003acbb353b9c79b70","target":"record","created_at":"2026-06-01T01:02:19Z","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":"7a331287be74db049c5c392a873cc5bcc854bbd6b2028bb7cb7e48e620c88e73","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T16:37:42Z","title_canon_sha256":"f05bf2a1e623672d8270279b401380b8af0076ece991b947bb8e359580c87c9b"},"schema_version":"1.0","source":{"id":"2508.21762","kind":"arxiv","version":4}},"canonical_sha256":"d065625091cbbd1917fc8652b585b5ebffb53402ccb3ce0d974ee73dabd84ffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d065625091cbbd1917fc8652b585b5ebffb53402ccb3ce0d974ee73dabd84ffe","first_computed_at":"2026-06-01T01:02:19.866338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:19.866338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DD5/A7oBsGOe8VuKDKMGbssnivMVX1medOP2xb+JBl/vUcJT/BwhTPLW3Bdr5s17tn29Ijz5C9MUvjaxeuKvCQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:19.867230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21762","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27f3e5d4e648c4b52691bc8fb88e79af60563a48953a66003acbb353b9c79b70","sha256:fd58ab43aecabd6b6d417d6d2508713d83918426f9a360195ad6b7a868446e5c"],"state_sha256":"86ce94479aa433a771b433409d2b8eb8744f5446d6d1429a6ef526d233d5899a"}