{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YCW5M656WQN6RHL6BSR6V27B2U","short_pith_number":"pith:YCW5M656","canonical_record":{"source":{"id":"2606.05932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T09:35:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a483e70e3dbd69c82b8ecdaa644654ad4bef9daac0391248ec1cbd9587c4140a","abstract_canon_sha256":"10c66ef00ed80f178a2f38b9ad72182b180c0e85c0518d1ba3d4f7fb85a6fa96"},"schema_version":"1.0"},"canonical_sha256":"c0add67bbeb41be89d7e0ca3eaebe1d536b2b053f3514f0bf10b4dccb26210cd","source":{"kind":"arxiv","id":"2606.05932","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05932","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05932v1","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05932","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"YCW5M656WQN6","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"YCW5M656WQN6RHL6","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"YCW5M656","created_at":"2026-06-05T01:15:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YCW5M656WQN6RHL6BSR6V27B2U","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T09:35:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a483e70e3dbd69c82b8ecdaa644654ad4bef9daac0391248ec1cbd9587c4140a","abstract_canon_sha256":"10c66ef00ed80f178a2f38b9ad72182b180c0e85c0518d1ba3d4f7fb85a6fa96"},"schema_version":"1.0"},"canonical_sha256":"c0add67bbeb41be89d7e0ca3eaebe1d536b2b053f3514f0bf10b4dccb26210cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:28.096156Z","signature_b64":"z9BZ2RNeCMmGzCnnRRKSwSkQXNc23vIEynzpTpnSjDU4R4IA9RRcN5lNDxXNQDLuw5gtQWtk0yTaSSVxbdWNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0add67bbeb41be89d7e0ca3eaebe1d536b2b053f3514f0bf10b4dccb26210cd","last_reissued_at":"2026-06-05T01:15:28.095415Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:28.095415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05932","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":"2026-06-05T01:15:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QVhpHWmKbkYHnsU00vg6uMZJ0jnX4C7IjsmYQNallfU8p0BieHL3PiDhz0P+QEBZT3FsEH8VQzRWRkV6RYu+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T07:59:33.300517Z"},"content_sha256":"b1f002dcb5b24223b4a358b238362da5cfc6f5a196f64cfd3ed716d1ad20b288","schema_version":"1.0","event_id":"sha256:b1f002dcb5b24223b4a358b238362da5cfc6f5a196f64cfd3ed716d1ad20b288"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YCW5M656WQN6RHL6BSR6V27B2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Yuze Gao","submitted_at":"2026-06-04T09:35:54Z","abstract_excerpt":"Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier. Practitioners commonly interpret naive = acc(TRUE) - acc(RANDOM) as the reward-design effect. We prove this estimand is systematically biased: it conflates self-consistency elicitation (sharpening the policy toward its modal answer via majority pseudo-reward) with genuine reward-design signal. Using a controlled tabular-GRPO simulator we derive an exact telescoping decomposition total = null + eli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05932","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/2606.05932/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":"2026-06-05T01:15:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uNmH1usl8jzVrIwrCEPc74VoGwhQ+2uvUdXh5lBeZnTxiHfsPsWkxnyVjDLiGYMLNpczvDU2vi7qPQnzFxLHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T07:59:33.300933Z"},"content_sha256":"3a6f6eaf78891a9ee50116fa8132378db2cb1d73193c35f9e2be8e4b40b90688","schema_version":"1.0","event_id":"sha256:3a6f6eaf78891a9ee50116fa8132378db2cb1d73193c35f9e2be8e4b40b90688"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCW5M656WQN6RHL6BSR6V27B2U/bundle.json","state_url":"https://pith.science/pith/YCW5M656WQN6RHL6BSR6V27B2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCW5M656WQN6RHL6BSR6V27B2U/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":"2026-07-03T07:59:33Z","links":{"resolver":"https://pith.science/pith/YCW5M656WQN6RHL6BSR6V27B2U","bundle":"https://pith.science/pith/YCW5M656WQN6RHL6BSR6V27B2U/bundle.json","state":"https://pith.science/pith/YCW5M656WQN6RHL6BSR6V27B2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCW5M656WQN6RHL6BSR6V27B2U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YCW5M656WQN6RHL6BSR6V27B2U","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":"10c66ef00ed80f178a2f38b9ad72182b180c0e85c0518d1ba3d4f7fb85a6fa96","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T09:35:54Z","title_canon_sha256":"a483e70e3dbd69c82b8ecdaa644654ad4bef9daac0391248ec1cbd9587c4140a"},"schema_version":"1.0","source":{"id":"2606.05932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05932","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05932v1","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05932","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"YCW5M656WQN6","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"YCW5M656WQN6RHL6","created_at":"2026-06-05T01:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"YCW5M656","created_at":"2026-06-05T01:15:28Z"}],"graph_snapshots":[{"event_id":"sha256:3a6f6eaf78891a9ee50116fa8132378db2cb1d73193c35f9e2be8e4b40b90688","target":"graph","created_at":"2026-06-05T01:15:28Z","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/2606.05932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier. Practitioners commonly interpret naive = acc(TRUE) - acc(RANDOM) as the reward-design effect. We prove this estimand is systematically biased: it conflates self-consistency elicitation (sharpening the policy toward its modal answer via majority pseudo-reward) with genuine reward-design signal. Using a controlled tabular-GRPO simulator we derive an exact telescoping decomposition total = null + eli","authors_text":"Yuze Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T09:35:54Z","title":"A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05932","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:b1f002dcb5b24223b4a358b238362da5cfc6f5a196f64cfd3ed716d1ad20b288","target":"record","created_at":"2026-06-05T01:15:28Z","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":"10c66ef00ed80f178a2f38b9ad72182b180c0e85c0518d1ba3d4f7fb85a6fa96","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T09:35:54Z","title_canon_sha256":"a483e70e3dbd69c82b8ecdaa644654ad4bef9daac0391248ec1cbd9587c4140a"},"schema_version":"1.0","source":{"id":"2606.05932","kind":"arxiv","version":1}},"canonical_sha256":"c0add67bbeb41be89d7e0ca3eaebe1d536b2b053f3514f0bf10b4dccb26210cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0add67bbeb41be89d7e0ca3eaebe1d536b2b053f3514f0bf10b4dccb26210cd","first_computed_at":"2026-06-05T01:15:28.095415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:28.095415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z9BZ2RNeCMmGzCnnRRKSwSkQXNc23vIEynzpTpnSjDU4R4IA9RRcN5lNDxXNQDLuw5gtQWtk0yTaSSVxbdWNAA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:28.096156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1f002dcb5b24223b4a358b238362da5cfc6f5a196f64cfd3ed716d1ad20b288","sha256:3a6f6eaf78891a9ee50116fa8132378db2cb1d73193c35f9e2be8e4b40b90688"],"state_sha256":"3dee4c572beafa36d7544a3dea0c6d52d97ec74a7a2ba5372136997270fed0d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpznjjQWR9H0AH0Pu3FaYrfiEYXisNSp9MJZwLpu/pozTZv2o0eDNfQeRax3AljFpFV4n8dedoAfgnlSFGSzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T07:59:33.303365Z","bundle_sha256":"9287fdc4a84bae81c683d16058b75c7eeff867a0d4d73a08fd6d377ca0b80932"}}