{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ASXEDYXCXQWUYJBHHVUPEH7HAR","short_pith_number":"pith:ASXEDYXC","canonical_record":{"source":{"id":"2502.05234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T19:35:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce3b3350e654c6e0dd5386feed45fa02dd82193120f645a569ef5c4829050551","abstract_canon_sha256":"b7b70fb80d4e8800378021e0426beba0ee2d6f75d052d24d0c9aba8b74d10888"},"schema_version":"1.0"},"canonical_sha256":"04ae41e2e2bc2d4c24273d68f21fe704765de2bf73056f4ee0eddfaad0b67d10","source":{"kind":"arxiv","id":"2502.05234","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05234","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05234v2","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05234","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"ASXEDYXCXQWU","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"ASXEDYXCXQWUYJBH","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"ASXEDYXC","created_at":"2026-07-05T11:21:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ASXEDYXCXQWUYJBHHVUPEH7HAR","target":"record","payload":{"canonical_record":{"source":{"id":"2502.05234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T19:35:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce3b3350e654c6e0dd5386feed45fa02dd82193120f645a569ef5c4829050551","abstract_canon_sha256":"b7b70fb80d4e8800378021e0426beba0ee2d6f75d052d24d0c9aba8b74d10888"},"schema_version":"1.0"},"canonical_sha256":"04ae41e2e2bc2d4c24273d68f21fe704765de2bf73056f4ee0eddfaad0b67d10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:41.859275Z","signature_b64":"uNBOntNL1YzFbWx7OlSlV13+8UpvzBhVjNSiVmAA+5mpp3e21J+B+JuRuU7HfVMWu4HoteqQEs5TF9MAedltBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04ae41e2e2bc2d4c24273d68f21fe704765de2bf73056f4ee0eddfaad0b67d10","last_reissued_at":"2026-07-05T11:21:41.858703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:41.858703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.05234","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":"2026-07-05T11:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQieTN31opt7+Fa1Y+1ouYPh4jQ7BRnDQ+k7yJk3a3/JAIJKdzRMA7JZo2rxM9aNW9P91jCRO3Coh2nKRXmKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:00:07.897657Z"},"content_sha256":"c1de824ec40c37d64e1a0376fef4663447d94a385d1602d80f774daf7801816a","schema_version":"1.0","event_id":"sha256:c1de824ec40c37d64e1a0376fef4663447d94a385d1602d80f774daf7801816a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ASXEDYXCXQWUYJBHHVUPEH7HAR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Temperature for Language Models with Multi-Sample Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Sean Welleck, Weihua Du, Yiming Yang","submitted_at":"2025-02-07T19:35:25Z","abstract_excerpt":"Multi-sample aggregation strategies, such as majority voting and best-of-N sampling, are widely used in contemporary large language models (LLMs) to enhance predictive accuracy across various tasks. A key challenge in this process is temperature selection, which significantly impacts model performance. Existing approaches either rely on a fixed default temperature or require labeled validation data for tuning, which are often scarce and difficult to obtain. This paper addresses the challenge of automatically identifying the (near)-optimal temperature for different LLMs using multi-sample aggre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05234","kind":"arxiv","version":2},"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/2502.05234/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PlTyLtAbUrfN0AOgelI2sWMm5aJomjFxnulnNp+KmC6Ly0YlGxhWgq1IjDQ4XmyBgmDSo2SgSlorBnOdiF8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:00:07.898166Z"},"content_sha256":"164745ce857d010311a90abd76463ebb82891718ca0f95527fbde1bb3273a00e","schema_version":"1.0","event_id":"sha256:164745ce857d010311a90abd76463ebb82891718ca0f95527fbde1bb3273a00e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR/bundle.json","state_url":"https://pith.science/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR/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":"2026-08-08T14:00:07Z","links":{"resolver":"https://pith.science/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR","bundle":"https://pith.science/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR/bundle.json","state":"https://pith.science/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASXEDYXCXQWUYJBHHVUPEH7HAR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ASXEDYXCXQWUYJBHHVUPEH7HAR","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":"b7b70fb80d4e8800378021e0426beba0ee2d6f75d052d24d0c9aba8b74d10888","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T19:35:25Z","title_canon_sha256":"ce3b3350e654c6e0dd5386feed45fa02dd82193120f645a569ef5c4829050551"},"schema_version":"1.0","source":{"id":"2502.05234","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05234","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05234v2","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05234","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"pith_short_12","alias_value":"ASXEDYXCXQWU","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"pith_short_16","alias_value":"ASXEDYXCXQWUYJBH","created_at":"2026-07-05T11:21:41Z"},{"alias_kind":"pith_short_8","alias_value":"ASXEDYXC","created_at":"2026-07-05T11:21:41Z"}],"graph_snapshots":[{"event_id":"sha256:164745ce857d010311a90abd76463ebb82891718ca0f95527fbde1bb3273a00e","target":"graph","created_at":"2026-07-05T11:21:41Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.05234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-sample aggregation strategies, such as majority voting and best-of-N sampling, are widely used in contemporary large language models (LLMs) to enhance predictive accuracy across various tasks. A key challenge in this process is temperature selection, which significantly impacts model performance. Existing approaches either rely on a fixed default temperature or require labeled validation data for tuning, which are often scarce and difficult to obtain. This paper addresses the challenge of automatically identifying the (near)-optimal temperature for different LLMs using multi-sample aggre","authors_text":"Sean Welleck, Weihua Du, Yiming Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T19:35:25Z","title":"Optimizing Temperature for Language Models with Multi-Sample Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05234","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1de824ec40c37d64e1a0376fef4663447d94a385d1602d80f774daf7801816a","target":"record","created_at":"2026-07-05T11:21:41Z","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":"b7b70fb80d4e8800378021e0426beba0ee2d6f75d052d24d0c9aba8b74d10888","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T19:35:25Z","title_canon_sha256":"ce3b3350e654c6e0dd5386feed45fa02dd82193120f645a569ef5c4829050551"},"schema_version":"1.0","source":{"id":"2502.05234","kind":"arxiv","version":2}},"canonical_sha256":"04ae41e2e2bc2d4c24273d68f21fe704765de2bf73056f4ee0eddfaad0b67d10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04ae41e2e2bc2d4c24273d68f21fe704765de2bf73056f4ee0eddfaad0b67d10","first_computed_at":"2026-07-05T11:21:41.858703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:41.858703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNBOntNL1YzFbWx7OlSlV13+8UpvzBhVjNSiVmAA+5mpp3e21J+B+JuRuU7HfVMWu4HoteqQEs5TF9MAedltBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:41.859275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05234","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1de824ec40c37d64e1a0376fef4663447d94a385d1602d80f774daf7801816a","sha256:164745ce857d010311a90abd76463ebb82891718ca0f95527fbde1bb3273a00e"],"state_sha256":"8a39182b57ddefe23a203fea9a6584fbeab4ef822c53e3a58784b70697d2e764"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqeHAq/RmI0DhVHxVcFbOff1ZKlwNLT9NvugheaR09X/74BTxP6taUZr75wpHWvbpLYdsAeiluvhPPadv4ucBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:00:07.903022Z","bundle_sha256":"a6d3532ee11865d64a72cf1314ae8c7cd4463c3be69b8ccc3d6ebc72a3accb06"}}