{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V3M4SFXSY52J7HP6J5BLEXTB5T","short_pith_number":"pith:V3M4SFXS","canonical_record":{"source":{"id":"2508.04216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T08:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"1ae118c96f1f464f672aef09542eb9df1545c1d85d8b987d942728b9e1cef41d","abstract_canon_sha256":"46d5a09c236dbf57ccb0d52fc1a96f0a411ee7d996ed1c2c188398cb537d9c27"},"schema_version":"1.0"},"canonical_sha256":"aed9c916f2c7749f9dfe4f42b25e61ecdfbfcbdb6643edbb6fd4189ef6df2dea","source":{"kind":"arxiv","id":"2508.04216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04216","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04216v1","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04216","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"V3M4SFXSY52J","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"V3M4SFXSY52J7HP6","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"V3M4SFXS","created_at":"2026-07-05T11:49:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V3M4SFXSY52J7HP6J5BLEXTB5T","target":"record","payload":{"canonical_record":{"source":{"id":"2508.04216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T08:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"1ae118c96f1f464f672aef09542eb9df1545c1d85d8b987d942728b9e1cef41d","abstract_canon_sha256":"46d5a09c236dbf57ccb0d52fc1a96f0a411ee7d996ed1c2c188398cb537d9c27"},"schema_version":"1.0"},"canonical_sha256":"aed9c916f2c7749f9dfe4f42b25e61ecdfbfcbdb6643edbb6fd4189ef6df2dea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:23.043754Z","signature_b64":"gG5ouT3kN/6AKYClwZ8hH9pkCrqR/ogAhLDsHxXjjwKQ5dJnjKOLA14J2NMSInNr219KbbEdXGKyKmdMinI5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aed9c916f2c7749f9dfe4f42b25e61ecdfbfcbdb6643edbb6fd4189ef6df2dea","last_reissued_at":"2026-07-05T11:49:23.043257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:23.043257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.04216","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":"2026-07-05T11:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q1WbFpFy7lyui2qH78vcNXNqnZ/1nI6gCxZZNgOji2ClnOmk8JpCjxMhykYC137QQbMskitf+Hly8BUbmQggCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:07:13.453776Z"},"content_sha256":"5ce5d2aa0f9ec4d58157785f67b7b064bccb0c1fb11f22f59f8f7bcf638cbe74","schema_version":"1.0","event_id":"sha256:5ce5d2aa0f9ec4d58157785f67b7b064bccb0c1fb11f22f59f8f7bcf638cbe74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V3M4SFXSY52J7HP6J5BLEXTB5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huijie Guo, Ruike Song, Wenwen Qiang, Zeen Song","submitted_at":"2025-08-06T08:48:55Z","abstract_excerpt":"External reasoning systems combine language models with process reward models (PRMs) to select high-quality reasoning paths for complex tasks such as mathematical problem solving. However, these systems are prone to reward hacking, where high-scoring but logically incorrect paths are assigned high scores by the PRMs, leading to incorrect answers. From a causal inference perspective, we attribute this phenomenon primarily to the presence of confounding semantic features. To address it, we propose Causal Reward Adjustment (CRA), a method that mitigates reward hacking by estimating the true rewar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04216","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/2508.04216/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":"2026-07-05T11:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8z3fJB1PQeR5TybeTU/k7t8s9oupZT44u1s/fdRGbdn+2BpVTvAfafQGr3tGAoU7MFStdgNZZi6lhIL/6jpCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:07:13.454295Z"},"content_sha256":"c877033ca984dc9e75ed2e705e64dc3e56c67df24af65f7a906b4c1b57e73f38","schema_version":"1.0","event_id":"sha256:c877033ca984dc9e75ed2e705e64dc3e56c67df24af65f7a906b4c1b57e73f38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3M4SFXSY52J7HP6J5BLEXTB5T/bundle.json","state_url":"https://pith.science/pith/V3M4SFXSY52J7HP6J5BLEXTB5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3M4SFXSY52J7HP6J5BLEXTB5T/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":"2026-08-06T16:07:13Z","links":{"resolver":"https://pith.science/pith/V3M4SFXSY52J7HP6J5BLEXTB5T","bundle":"https://pith.science/pith/V3M4SFXSY52J7HP6J5BLEXTB5T/bundle.json","state":"https://pith.science/pith/V3M4SFXSY52J7HP6J5BLEXTB5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3M4SFXSY52J7HP6J5BLEXTB5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V3M4SFXSY52J7HP6J5BLEXTB5T","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":"46d5a09c236dbf57ccb0d52fc1a96f0a411ee7d996ed1c2c188398cb537d9c27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T08:48:55Z","title_canon_sha256":"1ae118c96f1f464f672aef09542eb9df1545c1d85d8b987d942728b9e1cef41d"},"schema_version":"1.0","source":{"id":"2508.04216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04216","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04216v1","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04216","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"V3M4SFXSY52J","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"V3M4SFXSY52J7HP6","created_at":"2026-07-05T11:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"V3M4SFXS","created_at":"2026-07-05T11:49:23Z"}],"graph_snapshots":[{"event_id":"sha256:c877033ca984dc9e75ed2e705e64dc3e56c67df24af65f7a906b4c1b57e73f38","target":"graph","created_at":"2026-07-05T11:49:23Z","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/2508.04216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"External reasoning systems combine language models with process reward models (PRMs) to select high-quality reasoning paths for complex tasks such as mathematical problem solving. However, these systems are prone to reward hacking, where high-scoring but logically incorrect paths are assigned high scores by the PRMs, leading to incorrect answers. From a causal inference perspective, we attribute this phenomenon primarily to the presence of confounding semantic features. To address it, we propose Causal Reward Adjustment (CRA), a method that mitigates reward hacking by estimating the true rewar","authors_text":"Huijie Guo, Ruike Song, Wenwen Qiang, Zeen Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T08:48:55Z","title":"Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04216","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":"sha256:5ce5d2aa0f9ec4d58157785f67b7b064bccb0c1fb11f22f59f8f7bcf638cbe74","target":"record","created_at":"2026-07-05T11:49:23Z","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":"46d5a09c236dbf57ccb0d52fc1a96f0a411ee7d996ed1c2c188398cb537d9c27","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T08:48:55Z","title_canon_sha256":"1ae118c96f1f464f672aef09542eb9df1545c1d85d8b987d942728b9e1cef41d"},"schema_version":"1.0","source":{"id":"2508.04216","kind":"arxiv","version":1}},"canonical_sha256":"aed9c916f2c7749f9dfe4f42b25e61ecdfbfcbdb6643edbb6fd4189ef6df2dea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aed9c916f2c7749f9dfe4f42b25e61ecdfbfcbdb6643edbb6fd4189ef6df2dea","first_computed_at":"2026-07-05T11:49:23.043257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:23.043257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gG5ouT3kN/6AKYClwZ8hH9pkCrqR/ogAhLDsHxXjjwKQ5dJnjKOLA14J2NMSInNr219KbbEdXGKyKmdMinI5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:23.043754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ce5d2aa0f9ec4d58157785f67b7b064bccb0c1fb11f22f59f8f7bcf638cbe74","sha256:c877033ca984dc9e75ed2e705e64dc3e56c67df24af65f7a906b4c1b57e73f38"],"state_sha256":"7748ecaeba4fb6fb005b8a7fade2bb92cc6da9100e5fd9ca81145f55ae6a45cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ah9KBkdpaHhLb/vQkgZVoOld6CG6AKf2T6oIyKcvm4gsPuFq5BtYPYh86pr2+nCaREIEm2qPFWYiHbOq2FCyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:07:13.459977Z","bundle_sha256":"3d04e71d7b79382878651224c067cf72079a3143d15fb070f32bac0b13c5e74d"}}