{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VEQTYDLWEMSR7E62TW2YF4VV3T","short_pith_number":"pith:VEQTYDLW","canonical_record":{"source":{"id":"2606.00869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T19:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"88e0d4e529c3d41b31149fad539e1175807a18b862ca20dc828536cc19b0abdf","abstract_canon_sha256":"e30a524583df99c77286ac4ab778221780ad8230cbdb916d6754be32a74000cb"},"schema_version":"1.0"},"canonical_sha256":"a9213c0d7623251f93da9db582f2b5dcdcdf17e828247b796234b4bc2db32eb2","source":{"kind":"arxiv","id":"2606.00869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00869","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00869v1","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00869","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"VEQTYDLWEMSR","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"VEQTYDLWEMSR7E62","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"VEQTYDLW","created_at":"2026-06-02T01:04:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VEQTYDLWEMSR7E62TW2YF4VV3T","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T19:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"88e0d4e529c3d41b31149fad539e1175807a18b862ca20dc828536cc19b0abdf","abstract_canon_sha256":"e30a524583df99c77286ac4ab778221780ad8230cbdb916d6754be32a74000cb"},"schema_version":"1.0"},"canonical_sha256":"a9213c0d7623251f93da9db582f2b5dcdcdf17e828247b796234b4bc2db32eb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:08.397253Z","signature_b64":"8eHz571r3/olfL96SNSTkCLELCcIxP2jgxSw2zFQ+5RI6hUwdXhm5Hpdztwb9+LaGALcZEK8pG5RE4MRoHaoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9213c0d7623251f93da9db582f2b5dcdcdf17e828247b796234b4bc2db32eb2","last_reissued_at":"2026-06-02T01:04:08.396851Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:08.396851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00869","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pB0nLwufxy0yL/KJ/6qbgXsYNooFHXkZfauG6gVBo5m+kPFzfh4z7PRO/KyjgioYDpiiIMX3O+VAumUbyi/qCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:57:04.451563Z"},"content_sha256":"d31598dcb3c3ffc9b0a685877c16e4568442260931cec8d41ed1f48ff5d260d6","schema_version":"1.0","event_id":"sha256:d31598dcb3c3ffc9b0a685877c16e4568442260931cec8d41ed1f48ff5d260d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VEQTYDLWEMSR7E62TW2YF4VV3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ante Wang, Fandong Meng, Fuwen Luo, Guangwen Yang, Hao Zhou, Jingyi Ren, Lin Gan, Weitao Li, Weizhi Ma, Xiaolong Wang, Xuanyu Lei, Yang Liu, Yuanchi Zhang, Yuanhang Liu","submitted_at":"2026-05-30T19:53:19Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when evidence or reasoning is unreliable. Existing SFT or RL methods mainly teach LLMs to refuse or express uncertainty at the response level, which can overfit abstention behavior rather than improve reasoning reliability. To address this limitation, we propose Cognitive Pairwise Training (CPT), a cognitive mid-training alignment stage that turns pairwise comparisons over reasoning traces into a reusable alignment signa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00869","kind":"arxiv","version":1},"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/2606.00869/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":"2026-06-02T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ghfVmlJBsYQ464GFvyIT111Eo2FA6QJQbt/87ZlsJvegqVU8Qm2JbRFy6hmoVExaJYHWKfUu63TUUlFqZfBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:57:04.451944Z"},"content_sha256":"8436540630d4c29e22a788281cc553a040c3c1377ac40a6c63942db57f51b68f","schema_version":"1.0","event_id":"sha256:8436540630d4c29e22a788281cc553a040c3c1377ac40a6c63942db57f51b68f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEQTYDLWEMSR7E62TW2YF4VV3T/bundle.json","state_url":"https://pith.science/pith/VEQTYDLWEMSR7E62TW2YF4VV3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEQTYDLWEMSR7E62TW2YF4VV3T/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":"2026-06-02T21:57:04Z","links":{"resolver":"https://pith.science/pith/VEQTYDLWEMSR7E62TW2YF4VV3T","bundle":"https://pith.science/pith/VEQTYDLWEMSR7E62TW2YF4VV3T/bundle.json","state":"https://pith.science/pith/VEQTYDLWEMSR7E62TW2YF4VV3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEQTYDLWEMSR7E62TW2YF4VV3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VEQTYDLWEMSR7E62TW2YF4VV3T","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":"e30a524583df99c77286ac4ab778221780ad8230cbdb916d6754be32a74000cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T19:53:19Z","title_canon_sha256":"88e0d4e529c3d41b31149fad539e1175807a18b862ca20dc828536cc19b0abdf"},"schema_version":"1.0","source":{"id":"2606.00869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00869","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00869v1","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00869","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"VEQTYDLWEMSR","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"VEQTYDLWEMSR7E62","created_at":"2026-06-02T01:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"VEQTYDLW","created_at":"2026-06-02T01:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:8436540630d4c29e22a788281cc553a040c3c1377ac40a6c63942db57f51b68f","target":"graph","created_at":"2026-06-02T01:04:08Z","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/2606.00869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when evidence or reasoning is unreliable. Existing SFT or RL methods mainly teach LLMs to refuse or express uncertainty at the response level, which can overfit abstention behavior rather than improve reasoning reliability. To address this limitation, we propose Cognitive Pairwise Training (CPT), a cognitive mid-training alignment stage that turns pairwise comparisons over reasoning traces into a reusable alignment signa","authors_text":"Ante Wang, Fandong Meng, Fuwen Luo, Guangwen Yang, Hao Zhou, Jingyi Ren, Lin Gan, Weitao Li, Weizhi Ma, Xiaolong Wang, Xuanyu Lei, Yang Liu, Yuanchi Zhang, Yuanhang Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T19:53:19Z","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00869","kind":"arxiv","version":1},"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:d31598dcb3c3ffc9b0a685877c16e4568442260931cec8d41ed1f48ff5d260d6","target":"record","created_at":"2026-06-02T01:04:08Z","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":"e30a524583df99c77286ac4ab778221780ad8230cbdb916d6754be32a74000cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T19:53:19Z","title_canon_sha256":"88e0d4e529c3d41b31149fad539e1175807a18b862ca20dc828536cc19b0abdf"},"schema_version":"1.0","source":{"id":"2606.00869","kind":"arxiv","version":1}},"canonical_sha256":"a9213c0d7623251f93da9db582f2b5dcdcdf17e828247b796234b4bc2db32eb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9213c0d7623251f93da9db582f2b5dcdcdf17e828247b796234b4bc2db32eb2","first_computed_at":"2026-06-02T01:04:08.396851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:08.396851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8eHz571r3/olfL96SNSTkCLELCcIxP2jgxSw2zFQ+5RI6hUwdXhm5Hpdztwb9+LaGALcZEK8pG5RE4MRoHaoDQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:08.397253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d31598dcb3c3ffc9b0a685877c16e4568442260931cec8d41ed1f48ff5d260d6","sha256:8436540630d4c29e22a788281cc553a040c3c1377ac40a6c63942db57f51b68f"],"state_sha256":"79edffd2fb5556743cb3587d6162ac14dea6b29c816d643d9a1ba597c92f1134"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8b1W/eVkpLnqocND77gzCu2p6MwTcLV+xict/g6/U5w0/SMeAPzqf7/3f7mQER5wQH1TzeTzt9Y9Z3f2hi05CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:57:04.454788Z","bundle_sha256":"fe0e55271a50866f27f6dbb37277ba01ffda95e2c861708f018c513a52f502c6"}}