{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QWHABWM5WU2ONX3LANLUMMT6G5","short_pith_number":"pith:QWHABWM5","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"},"canonical_sha256":"858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5","source":{"kind":"arxiv","id":"2604.17433","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17433","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17433v2","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17433","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"QWHABWM5WU2O","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"QWHABWM5WU2ONX3L","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"QWHABWM5","created_at":"2026-06-08T01:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QWHABWM5WU2ONX3LANLUMMT6G5","target":"record","payload":{"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"},"canonical_sha256":"858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5","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"},"source_kind":"arxiv","source_id":"2604.17433","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y81NT86+mKBDyEYjJC3DWLtBCEaoNNVJqspOIEPC+Dg34X+trss5Gs28c/UUJEAUzikMKRHAjP1PNYE15YcPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:44:42.114201Z"},"content_sha256":"0686527de4e2c141a0834310979564cda09d26874368715e71b4fb7dbf08d7a6","schema_version":"1.0","event_id":"sha256:0686527de4e2c141a0834310979564cda09d26874368715e71b4fb7dbf08d7a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QWHABWM5WU2ONX3LANLUMMT6G5","target":"graph","payload":{"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"},"verdict_id":"feb6b808-20e4-43f4-858c-ca715a8382db"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"URD2jBLNrDkEM6d3WiMPF4N6ymDS6FmHM0F6oY214SpN7b027fvlwPkQNRB0KwNlw/jtBEJqBXNPLqeUmE2kBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:44:42.114670Z"},"content_sha256":"c449054651c98bc7c48cba64fe37973685d3a71095e6597d9ca7f0c2f7089e3b","schema_version":"1.0","event_id":"sha256:c449054651c98bc7c48cba64fe37973685d3a71095e6597d9ca7f0c2f7089e3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/bundle.json","state_url":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QWHABWM5WU2ONX3LANLUMMT6G5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T15:44:42Z","links":{"resolver":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5","bundle":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/bundle.json","state":"https://pith.science/pith/QWHABWM5WU2ONX3LANLUMMT6G5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QWHABWM5WU2ONX3LANLUMMT6G5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QWHABWM5WU2ONX3LANLUMMT6G5","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":"dbce1aacf91604acd645fe32afc726af664aa40b9c279d95d4a9dc5975db7dd3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T13:26:04Z","title_canon_sha256":"a9fd41b9e06820428d3d1acad47bac315c3f27c9739baef71a919b65c4b77778"},"schema_version":"1.0","source":{"id":"2604.17433","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17433","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17433v2","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17433","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"QWHABWM5WU2O","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"QWHABWM5WU2ONX3L","created_at":"2026-06-08T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"QWHABWM5","created_at":"2026-06-08T01:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:c449054651c98bc7c48cba64fe37973685d3a71095e6597d9ca7f0c2f7089e3b","target":"graph","created_at":"2026-06-08T01:04:05Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy."}],"snapshot_sha256":"c6e0dcf4bda387a986baee7ec0d0d37fbc37dec72d2195d67574b9a5da52d385"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.17433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Majd Hawasly, Md Rizwan Parvez, Mohammad Raza, Raman Saparkhan","cross_cats":["cs.AI","cs.LG"],"headline":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T13:26:04Z","title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17433","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T05:36:51.832748Z","id":"feb6b808-20e4-43f4-858c-ca715a8382db","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CoT-PoT ensembling cuts the samples needed for LLM self-consistency by 9.3 times while raising accuracy.","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.","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."}},"verdict_id":"feb6b808-20e4-43f4-858c-ca715a8382db"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0686527de4e2c141a0834310979564cda09d26874368715e71b4fb7dbf08d7a6","target":"record","created_at":"2026-06-08T01:04:05Z","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":"dbce1aacf91604acd645fe32afc726af664aa40b9c279d95d4a9dc5975db7dd3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T13:26:04Z","title_canon_sha256":"a9fd41b9e06820428d3d1acad47bac315c3f27c9739baef71a919b65c4b77778"},"schema_version":"1.0","source":{"id":"2604.17433","kind":"arxiv","version":2}},"canonical_sha256":"858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"858e00d99db534e6df6b035746327e3753e2c8efbcd59aafd69fe45a91df95c5","first_computed_at":"2026-06-08T01:04:05.108686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:05.108686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oA0urYXdP4irKIWolHYMEvgoX25ghLlIKC0MYPl3/VPlozLU35Go/xJc5WN1m/yrkOYs1RIy5pR7xlmJbW3nAA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:05.109543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17433","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0686527de4e2c141a0834310979564cda09d26874368715e71b4fb7dbf08d7a6","sha256:c449054651c98bc7c48cba64fe37973685d3a71095e6597d9ca7f0c2f7089e3b"],"state_sha256":"0ddd86ec67e3f70a3035dec4125f02234c523acef1c62bea557b578ffacc93dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"POLIN0LtJZC/47rVlQcX3yPbh1WXS9CIv7Z1TIsgTtLS6554JJQn59RhaROkvjPQL1aH9gnYF+EG2mgEH5mzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:44:42.116860Z","bundle_sha256":"d069867880b10d8689ab964a8a2ff4db39b087341ba1ec9ed27541b57e1722b5"}}