{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SKH5THI64JH4L5276KGXB7YPWT","short_pith_number":"pith:SKH5THI6","canonical_record":{"source":{"id":"2504.07527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:50:03Z","cross_cats_sorted":[],"title_canon_sha256":"eceecbf4b2dbe02dea068890ad4b9359f7acd7ce695f95c65d2d8f56888b358b","abstract_canon_sha256":"e0c44422d2e70ce317396412655aca523bc8b1e87b1a11dc5112550ff8348dd6"},"schema_version":"1.0"},"canonical_sha256":"928fd99d1ee24fc5f75ff28d70ff0fb4d6702a68bee720e9b626e6c4c42dc154","source":{"kind":"arxiv","id":"2504.07527","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07527","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07527v2","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07527","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"SKH5THI64JH4","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"SKH5THI64JH4L527","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"SKH5THI6","created_at":"2026-07-05T11:13:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SKH5THI64JH4L5276KGXB7YPWT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:50:03Z","cross_cats_sorted":[],"title_canon_sha256":"eceecbf4b2dbe02dea068890ad4b9359f7acd7ce695f95c65d2d8f56888b358b","abstract_canon_sha256":"e0c44422d2e70ce317396412655aca523bc8b1e87b1a11dc5112550ff8348dd6"},"schema_version":"1.0"},"canonical_sha256":"928fd99d1ee24fc5f75ff28d70ff0fb4d6702a68bee720e9b626e6c4c42dc154","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:23.892481Z","signature_b64":"F1oqJ+2Mcjmq+m1BpR9S8wXzt2mUJJ4w/VrH4aGo5YMxTUbPJ9fAXZUZDTjgGgZ0vg7RIBTcRQ+RiU4fC4POCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"928fd99d1ee24fc5f75ff28d70ff0fb4d6702a68bee720e9b626e6c4c42dc154","last_reissued_at":"2026-07-05T11:13:23.891765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:23.891765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07527","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":"2026-07-05T11:13:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VAiAFeiOiZw0jfmD88vdfASOaw7I6uFkIwwJE/GZeYEmV0umgwE1ASmatZFpUNG/bhKq09py34EukwyFRNOcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:23:57.210965Z"},"content_sha256":"648f82d975a74cfb989dc183a61ce54bb7a72e20d7316c184a8df75b1ebf14fe","schema_version":"1.0","event_id":"sha256:648f82d975a74cfb989dc183a61ce54bb7a72e20d7316c184a8df75b1ebf14fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SKH5THI64JH4L5276KGXB7YPWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Fei Huang, Junjie Zhang, Rushuai Yang, Shunyu Liu, Ting-En Lin, Yi Chen, Yongbin Li","submitted_at":"2025-04-10T07:50:03Z","abstract_excerpt":"In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit $Q$-function for inference. Through this theoretical lens, we demonstrate that the widely used beam search method suffers from unacceptable over-optimism, where inference errors are inevitably amplified due to inflated $Q$-value estimations of suboptimal steps. To address this limitation, we propose Supervised Optimism Correction(SOC), which introduces a simple yet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07527","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/2504.07527/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":"2026-07-05T11:13:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2qpgQVsqQc4aQbhqnQ3iM6gPu5TM5iu9YmKqLtVs2c0QqbKFY3eISs+tut+gDib/Yc2HsOZybv+iaLLriku0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:23:57.211930Z"},"content_sha256":"6c968a45e8dc629034b5053920dfad037b5a6de6b10c174976167f8895405771","schema_version":"1.0","event_id":"sha256:6c968a45e8dc629034b5053920dfad037b5a6de6b10c174976167f8895405771"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKH5THI64JH4L5276KGXB7YPWT/bundle.json","state_url":"https://pith.science/pith/SKH5THI64JH4L5276KGXB7YPWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKH5THI64JH4L5276KGXB7YPWT/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":"2026-08-07T06:23:57Z","links":{"resolver":"https://pith.science/pith/SKH5THI64JH4L5276KGXB7YPWT","bundle":"https://pith.science/pith/SKH5THI64JH4L5276KGXB7YPWT/bundle.json","state":"https://pith.science/pith/SKH5THI64JH4L5276KGXB7YPWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKH5THI64JH4L5276KGXB7YPWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SKH5THI64JH4L5276KGXB7YPWT","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":"e0c44422d2e70ce317396412655aca523bc8b1e87b1a11dc5112550ff8348dd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:50:03Z","title_canon_sha256":"eceecbf4b2dbe02dea068890ad4b9359f7acd7ce695f95c65d2d8f56888b358b"},"schema_version":"1.0","source":{"id":"2504.07527","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07527","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07527v2","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07527","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"SKH5THI64JH4","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"SKH5THI64JH4L527","created_at":"2026-07-05T11:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"SKH5THI6","created_at":"2026-07-05T11:13:23Z"}],"graph_snapshots":[{"event_id":"sha256:6c968a45e8dc629034b5053920dfad037b5a6de6b10c174976167f8895405771","target":"graph","created_at":"2026-07-05T11:13:23Z","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/2504.07527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit $Q$-function for inference. Through this theoretical lens, we demonstrate that the widely used beam search method suffers from unacceptable over-optimism, where inference errors are inevitably amplified due to inflated $Q$-value estimations of suboptimal steps. To address this limitation, we propose Supervised Optimism Correction(SOC), which introduces a simple yet","authors_text":"Dacheng Tao, Fei Huang, Junjie Zhang, Rushuai Yang, Shunyu Liu, Ting-En Lin, Yi Chen, Yongbin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:50:03Z","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07527","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":"sha256:648f82d975a74cfb989dc183a61ce54bb7a72e20d7316c184a8df75b1ebf14fe","target":"record","created_at":"2026-07-05T11:13:23Z","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":"e0c44422d2e70ce317396412655aca523bc8b1e87b1a11dc5112550ff8348dd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T07:50:03Z","title_canon_sha256":"eceecbf4b2dbe02dea068890ad4b9359f7acd7ce695f95c65d2d8f56888b358b"},"schema_version":"1.0","source":{"id":"2504.07527","kind":"arxiv","version":2}},"canonical_sha256":"928fd99d1ee24fc5f75ff28d70ff0fb4d6702a68bee720e9b626e6c4c42dc154","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"928fd99d1ee24fc5f75ff28d70ff0fb4d6702a68bee720e9b626e6c4c42dc154","first_computed_at":"2026-07-05T11:13:23.891765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:23.891765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F1oqJ+2Mcjmq+m1BpR9S8wXzt2mUJJ4w/VrH4aGo5YMxTUbPJ9fAXZUZDTjgGgZ0vg7RIBTcRQ+RiU4fC4POCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:23.892481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07527","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:648f82d975a74cfb989dc183a61ce54bb7a72e20d7316c184a8df75b1ebf14fe","sha256:6c968a45e8dc629034b5053920dfad037b5a6de6b10c174976167f8895405771"],"state_sha256":"9bc417a7a08e9b65fd8fb84dbd08fc5daf024aaffd1aafdfdce0de4463674bff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tWoW7u7HJr9IySfKUJhzl5bfWqB+07pnu97df+bXfNeqs4k5iMTyGhT2/bQKqyo+YySbZy7teainEaAq3TxCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:23:57.218515Z","bundle_sha256":"019e0025d938d53ba5039f9261ec45ebcb03d29c7a858f211821116b44270249"}}