{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5U4QZYLBATHM5NWVQ3PRK7JIS","short_pith_number":"pith:F5U4QZYL","schema_version":"1.0","canonical_sha256":"2f69c8670b08267675b6ac36f8abe9448b021829af40ff3d83cf661427345380","source":{"kind":"arxiv","id":"2605.25394","version":1},"attestation_state":"computed","paper":{"title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ashwath Vaithinathan Aravindan, Mayank Kejriwal","submitted_at":"2026-05-25T03:38:54Z","abstract_excerpt":"Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation amplify the need for reliable uncertainty detection. We propose _Second Guess_, a lightweight, parameter-free prompting technique for abstention in multiple-choice question answering (MCQA) that is well-suited for SLMs. Our key empirical insight is that models which truly know an answer will select it consistently, while uncertain models exhibit unstable behavior "},"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":"2605.25394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T03:38:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"462b5853500e8a84b8cad02b338cba17de923a60b1d0b614b471f249af9db162","abstract_canon_sha256":"037af030c4d081668e9f36c45beae041d1cc1a12235cd8461184ceb46740187c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:32.512545Z","signature_b64":"mhn2bbC2kpyaJeGUmXpix8Hc55up83U+TkFU4lYT+0gYBf7r7R5wUWWKdctamLDUl1ZQP1m75MjuPx7m7xGlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f69c8670b08267675b6ac36f8abe9448b021829af40ff3d83cf661427345380","last_reissued_at":"2026-05-26T02:04:32.511962Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:32.511962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ashwath Vaithinathan Aravindan, Mayank Kejriwal","submitted_at":"2026-05-25T03:38:54Z","abstract_excerpt":"Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation amplify the need for reliable uncertainty detection. We propose _Second Guess_, a lightweight, parameter-free prompting technique for abstention in multiple-choice question answering (MCQA) that is well-suited for SLMs. Our key empirical insight is that models which truly know an answer will select it consistently, while uncertain models exhibit unstable behavior "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25394","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/2605.25394/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":"2605.25394","created_at":"2026-05-26T02:04:32.512053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25394v1","created_at":"2026-05-26T02:04:32.512053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25394","created_at":"2026-05-26T02:04:32.512053+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5U4QZYLBATH","created_at":"2026-05-26T02:04:32.512053+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5U4QZYLBATHM5NW","created_at":"2026-05-26T02:04:32.512053+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5U4QZYL","created_at":"2026-05-26T02:04:32.512053+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/F5U4QZYLBATHM5NWVQ3PRK7JIS","json":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS.json","graph_json":"https://pith.science/api/pith-number/F5U4QZYLBATHM5NWVQ3PRK7JIS/graph.json","events_json":"https://pith.science/api/pith-number/F5U4QZYLBATHM5NWVQ3PRK7JIS/events.json","paper":"https://pith.science/paper/F5U4QZYL"},"agent_actions":{"view_html":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS","download_json":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS.json","view_paper":"https://pith.science/paper/F5U4QZYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25394&json=true","fetch_graph":"https://pith.science/api/pith-number/F5U4QZYLBATHM5NWVQ3PRK7JIS/graph.json","fetch_events":"https://pith.science/api/pith-number/F5U4QZYLBATHM5NWVQ3PRK7JIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS/action/storage_attestation","attest_author":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS/action/author_attestation","sign_citation":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS/action/citation_signature","submit_replication":"https://pith.science/pith/F5U4QZYLBATHM5NWVQ3PRK7JIS/action/replication_record"}},"created_at":"2026-05-26T02:04:32.512053+00:00","updated_at":"2026-05-26T02:04:32.512053+00:00"}