{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VZRWU3YUDJPYB3T5VGM72KQWRW","short_pith_number":"pith:VZRWU3YU","schema_version":"1.0","canonical_sha256":"ae636a6f141a5f80ee7da999fd2a168d996ef89c4fae12a8f31e30b8420b3ac1","source":{"kind":"arxiv","id":"2408.13457","version":3},"attestation_state":"computed","paper":{"title":"Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyuan Pan, Chuyi Tan, Kan Li, Peiwen Yuan, Shaoxiong Feng, Xinglin Wang, Yao Hu, Yiwei Li, Yueqi Zhang","submitted_at":"2024-08-24T04:03:35Z","abstract_excerpt":"Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset size. Its variants, Adaptive self-consistency (ASC) and Early-stopping self-consistency (ESC), dynamically adjust the number of samples based on the posterior distribution of a set of pre-samples, reducing the cost of SC with minimal impact on performance. Both methods, however, do not exploit the prior information about question difficulty. It often results in unnecessary rep"},"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":"2408.13457","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-24T04:03:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a443160bbdda3254cb397c450a1436ca25266229511612ddb974295c4b99fe75","abstract_canon_sha256":"1a754df01557023cb536fb8b0b570632937d9f572c18ce8ce12a67a500a6cbea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:02.974102Z","signature_b64":"QydEczJ+7+BQy5elVelTJd/sxN1RE0qXk4vA/ekjMEEXSaxhb44n7FM4qFE6cMdk4+6Mopopyhdae9SrMF8fDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae636a6f141a5f80ee7da999fd2a168d996ef89c4fae12a8f31e30b8420b3ac1","last_reissued_at":"2026-07-05T10:13:02.973598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:02.973598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyuan Pan, Chuyi Tan, Kan Li, Peiwen Yuan, Shaoxiong Feng, Xinglin Wang, Yao Hu, Yiwei Li, Yueqi Zhang","submitted_at":"2024-08-24T04:03:35Z","abstract_excerpt":"Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset size. Its variants, Adaptive self-consistency (ASC) and Early-stopping self-consistency (ESC), dynamically adjust the number of samples based on the posterior distribution of a set of pre-samples, reducing the cost of SC with minimal impact on performance. Both methods, however, do not exploit the prior information about question difficulty. It often results in unnecessary rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13457","kind":"arxiv","version":3},"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/2408.13457/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":"2408.13457","created_at":"2026-07-05T10:13:02.973660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13457v3","created_at":"2026-07-05T10:13:02.973660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13457","created_at":"2026-07-05T10:13:02.973660+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZRWU3YUDJPY","created_at":"2026-07-05T10:13:02.973660+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZRWU3YUDJPYB3T5","created_at":"2026-07-05T10:13:02.973660+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZRWU3YU","created_at":"2026-07-05T10:13:02.973660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06871","citing_title":"Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16419","citing_title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2412.21187","citing_title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06165","citing_title":"Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01194","citing_title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18839","citing_title":"One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW","json":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW.json","graph_json":"https://pith.science/api/pith-number/VZRWU3YUDJPYB3T5VGM72KQWRW/graph.json","events_json":"https://pith.science/api/pith-number/VZRWU3YUDJPYB3T5VGM72KQWRW/events.json","paper":"https://pith.science/paper/VZRWU3YU"},"agent_actions":{"view_html":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW","download_json":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW.json","view_paper":"https://pith.science/paper/VZRWU3YU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13457&json=true","fetch_graph":"https://pith.science/api/pith-number/VZRWU3YUDJPYB3T5VGM72KQWRW/graph.json","fetch_events":"https://pith.science/api/pith-number/VZRWU3YUDJPYB3T5VGM72KQWRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW/action/storage_attestation","attest_author":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW/action/author_attestation","sign_citation":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW/action/citation_signature","submit_replication":"https://pith.science/pith/VZRWU3YUDJPYB3T5VGM72KQWRW/action/replication_record"}},"created_at":"2026-07-05T10:13:02.973660+00:00","updated_at":"2026-07-05T10:13:02.973660+00:00"}