{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FRIBUOCEHYMKYEKLKVQNKOZ2VX","short_pith_number":"pith:FRIBUOCE","schema_version":"1.0","canonical_sha256":"2c501a38443e18ac114b5560d53b3aade0971f00adad90d8803446438e4a5a6f","source":{"kind":"arxiv","id":"2608.03401","version":1},"attestation_state":"computed","paper":{"title":"Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andres Algaba, Francesca Carlon, Vincent Ginis","submitted_at":"2026-08-04T09:54:37Z","abstract_excerpt":"Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, but a shorter trace may only show that the model stopped sooner. Here, we evaluate paired runs of the same question at matched reasoning horizons across 198 GPQA Diamond and 500 MMLU-Pro questions. We test a numeric/concision prompt that announces a token limit for Qwen3-14B and the trained effort settings of gpt-oss-20b and -120b. The Qwen prompt shortens reasoning traces by 12-17%, while accuracy changes at matched token limits are small and mix"},"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":"2608.03401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T09:54:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c210037564f461df1eb1565768ef1bf95b5fb22f28c1ec325a7ec27b1810a2c5","abstract_canon_sha256":"41ea42178a79f101f642ecabf1b6912785b6c7f173c46cb82418908ba80a0cfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:46.233638Z","signature_b64":"bRaeUDW8EQvPT3dVxluxrQGTtXRWnJy97HSceD2guMRCO+65SHC8KXCCR1loVdT+RdiYLm71v80dEyDHATLjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c501a38443e18ac114b5560d53b3aade0971f00adad90d8803446438e4a5a6f","last_reissued_at":"2026-08-05T01:35:46.232251Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:46.232251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andres Algaba, Francesca Carlon, Vincent Ginis","submitted_at":"2026-08-04T09:54:37Z","abstract_excerpt":"Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, but a shorter trace may only show that the model stopped sooner. Here, we evaluate paired runs of the same question at matched reasoning horizons across 198 GPQA Diamond and 500 MMLU-Pro questions. We test a numeric/concision prompt that announces a token limit for Qwen3-14B and the trained effort settings of gpt-oss-20b and -120b. The Qwen prompt shortens reasoning traces by 12-17%, while accuracy changes at matched token limits are small and mix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03401","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/2608.03401/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":"2608.03401","created_at":"2026-08-05T01:35:46.232675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03401v1","created_at":"2026-08-05T01:35:46.232675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03401","created_at":"2026-08-05T01:35:46.232675+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRIBUOCEHYMK","created_at":"2026-08-05T01:35:46.232675+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRIBUOCEHYMKYEKL","created_at":"2026-08-05T01:35:46.232675+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRIBUOCE","created_at":"2026-08-05T01:35:46.232675+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/FRIBUOCEHYMKYEKLKVQNKOZ2VX","json":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX.json","graph_json":"https://pith.science/api/pith-number/FRIBUOCEHYMKYEKLKVQNKOZ2VX/graph.json","events_json":"https://pith.science/api/pith-number/FRIBUOCEHYMKYEKLKVQNKOZ2VX/events.json","paper":"https://pith.science/paper/FRIBUOCE"},"agent_actions":{"view_html":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX","download_json":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX.json","view_paper":"https://pith.science/paper/FRIBUOCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03401&json=true","fetch_graph":"https://pith.science/api/pith-number/FRIBUOCEHYMKYEKLKVQNKOZ2VX/graph.json","fetch_events":"https://pith.science/api/pith-number/FRIBUOCEHYMKYEKLKVQNKOZ2VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX/action/storage_attestation","attest_author":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX/action/author_attestation","sign_citation":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX/action/citation_signature","submit_replication":"https://pith.science/pith/FRIBUOCEHYMKYEKLKVQNKOZ2VX/action/replication_record"}},"created_at":"2026-08-05T01:35:46.232675+00:00","updated_at":"2026-08-05T01:35:46.232675+00:00"}