{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QWHABWM5WU2ONX3LANLUMMT6G5","short_pith_number":"pith:QWHABWM5","schema_version":"1.0","canonical_sha256":"858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5","source":{"kind":"arxiv","id":"2604.17433","version":2},"attestation_state":"computed","paper":{"title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Majd Hawasly, Md Rizwan Parvez, Mohammad Raza, Raman Saparkhan","submitted_at":"2026-04-19T13:26:04Z","abstract_excerpt":"Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not o"},"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":"2604.17433","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T13:26:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a9fd41b9e06820428d3d1acad47bac315c3f27c9739baef71a919b65c4b77778","abstract_canon_sha256":"dbce1aacf91604acd645fe32afc726af664aa40b9c279d95d4a9dc5975db7dd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:05.109543Z","signature_b64":"oA0urYXdP4irKIWolHYMEvgoX25ghLlIKC0MYPl3/VPlozLU35Go/xJc5WN1m/yrkOYs1RIy5pR7xlmJbW3nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5","last_reissued_at":"2026-06-08T01:04:05.108686Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:05.108686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Majd Hawasly, Md Rizwan Parvez, Mohammad Raza, Raman Saparkhan","submitted_at":"2026-04-19T13:26:04Z","abstract_excerpt":"Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not o"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that Chain-of-Thought and Program-of-Thought outputs are sufficiently complementary and that their agreement reliably indicates correctness without needing many more samples or introducing new error modes; this is implicit in the early-stopping and ensembling strategies described.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c6e0dcf4bda387a986baee7ec0d0d37fbc37dec72d2195d67574b9a5da52d385"},"source":{"id":"2604.17433","kind":"arxiv","version":2},"verdict":{"id":"feb6b808-20e4-43f4-858c-ca715a8382db","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T05:36:51.832748Z","strongest_claim":"CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.","one_line_summary":"CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that Chain-of-Thought and Program-of-Thought outputs are sufficiently complementary and that their agreement reliably indicates correctness without needing many more samples or introducing new error modes; this is implicit in the early-stopping and ensembling strategies described.","pith_extraction_headline":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17433/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":"2604.17433","created_at":"2026-06-08T01:04:05.108818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.17433v2","created_at":"2026-06-08T01:04:05.108818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17433","created_at":"2026-06-08T01:04:05.108818+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWHABWM5WU2O","created_at":"2026-06-08T01:04:05.108818+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWHABWM5WU2ONX3L","created_at":"2026-06-08T01:04:05.108818+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWHABWM5","created_at":"2026-06-08T01:04:05.108818+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/QWHABWM5WU2ONX3LANLUMMT6G5","json":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5.json","graph_json":"https://pith.science/api/pith-number/QWHABWM5WU2ONX3LANLUMMT6G5/graph.json","events_json":"https://pith.science/api/pith-number/QWHABWM5WU2ONX3LANLUMMT6G5/events.json","paper":"https://pith.science/paper/QWHABWM5"},"agent_actions":{"view_html":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5","download_json":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5.json","view_paper":"https://pith.science/paper/QWHABWM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.17433&json=true","fetch_graph":"https://pith.science/api/pith-number/QWHABWM5WU2ONX3LANLUMMT6G5/graph.json","fetch_events":"https://pith.science/api/pith-number/QWHABWM5WU2ONX3LANLUMMT6G5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/action/storage_attestation","attest_author":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/action/author_attestation","sign_citation":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/action/citation_signature","submit_replication":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/action/replication_record"}},"created_at":"2026-06-08T01:04:05.108818+00:00","updated_at":"2026-06-08T01:04:05.108818+00:00"}