{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CZ2YV4EM5277FB6RZJZXUO4LFP","short_pith_number":"pith:CZ2YV4EM","canonical_record":{"source":{"id":"2607.27888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"605c0a3badf5c256b6c1f8481a7aa2bf07ced061fef454e684b6822d843ae9b8","abstract_canon_sha256":"c936fe9a143a2130a48151f1935d0263d70983efd66b3dfa0d67d49c987e8b6c"},"schema_version":"1.0"},"canonical_sha256":"16758af08ceebff287d1ca737a3b8b2be68434e5cabcb78cb26cac193bb9105c","source":{"kind":"arxiv","id":"2607.27888","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27888","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27888v1","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27888","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"CZ2YV4EM5277","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"pith_short_16","alias_value":"CZ2YV4EM5277FB6R","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"pith_short_8","alias_value":"CZ2YV4EM","created_at":"2026-07-31T01:34:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CZ2YV4EM5277FB6RZJZXUO4LFP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"605c0a3badf5c256b6c1f8481a7aa2bf07ced061fef454e684b6822d843ae9b8","abstract_canon_sha256":"c936fe9a143a2130a48151f1935d0263d70983efd66b3dfa0d67d49c987e8b6c"},"schema_version":"1.0"},"canonical_sha256":"16758af08ceebff287d1ca737a3b8b2be68434e5cabcb78cb26cac193bb9105c","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16758af08ceebff287d1ca737a3b8b2be68434e5cabcb78cb26cac193bb9105c","last_reissued_at":"2026-07-31T01:34:34.623236Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:34:34.623236Z"},"source_kind":"arxiv","source_id":"2607.27888","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":"2026-07-31T01:34:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Z6z50jZBdXzWjvSUj5Xzv3A960z/ymIJ5ZPdNl1OheJtZIABNSdMwGYhyaNiQbimgUVVPg904L9j1aURBDeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:10:51.923579Z"},"content_sha256":"253cbc11de0dd7a3f157b2526b5e7508a3c1f29cfdabef6661629cf5f55f42db","schema_version":"1.0","event_id":"sha256:253cbc11de0dd7a3f157b2526b5e7508a3c1f29cfdabef6661629cf5f55f42db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CZ2YV4EM5277FB6RZJZXUO4LFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Qiangqiang He, Zhongheng Wu, Zijian Wang","submitted_at":"2026-07-30T09:03:33Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) is central to improving long-CoT reasoning in large language models. Critic-free methods such as GRPO convert response-level rewards into advantages and uniformly broadcast them across tokens, overlooking their unequal contributions to the final outcome. On-policy self-distillation (OPSD) instead provides dense distributional supervision by minimizing the forward KL divergence between an unprivileged policy and a privileged self-teacher, implicitly assuming that the resulting likelihood shifts encode reliable answer-aligned information. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27888","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/2607.27888/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":"2026-07-31T01:34:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHlgK6q1N7m8zWrh8DGuiSp+xPEKsYyW2EwmC2o9R7PCnzYoMRCx6PN0YlIuF6cvPl3FKlMlFiB7om075dcQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:10:51.924073Z"},"content_sha256":"7d026555226a108cb5321e415338b190b59c20f029616bf49c266a1bd12d8cde","schema_version":"1.0","event_id":"sha256:7d026555226a108cb5321e415338b190b59c20f029616bf49c266a1bd12d8cde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ2YV4EM5277FB6RZJZXUO4LFP/bundle.json","state_url":"https://pith.science/pith/CZ2YV4EM5277FB6RZJZXUO4LFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ2YV4EM5277FB6RZJZXUO4LFP/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":"2026-08-03T22:10:51Z","links":{"resolver":"https://pith.science/pith/CZ2YV4EM5277FB6RZJZXUO4LFP","bundle":"https://pith.science/pith/CZ2YV4EM5277FB6RZJZXUO4LFP/bundle.json","state":"https://pith.science/pith/CZ2YV4EM5277FB6RZJZXUO4LFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ2YV4EM5277FB6RZJZXUO4LFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CZ2YV4EM5277FB6RZJZXUO4LFP","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":"c936fe9a143a2130a48151f1935d0263d70983efd66b3dfa0d67d49c987e8b6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:03:33Z","title_canon_sha256":"605c0a3badf5c256b6c1f8481a7aa2bf07ced061fef454e684b6822d843ae9b8"},"schema_version":"1.0","source":{"id":"2607.27888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27888","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27888v1","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27888","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"CZ2YV4EM5277","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"pith_short_16","alias_value":"CZ2YV4EM5277FB6R","created_at":"2026-07-31T01:34:34Z"},{"alias_kind":"pith_short_8","alias_value":"CZ2YV4EM","created_at":"2026-07-31T01:34:34Z"}],"graph_snapshots":[{"event_id":"sha256:7d026555226a108cb5321e415338b190b59c20f029616bf49c266a1bd12d8cde","target":"graph","created_at":"2026-07-31T01:34:34Z","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/2607.27888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) is central to improving long-CoT reasoning in large language models. Critic-free methods such as GRPO convert response-level rewards into advantages and uniformly broadcast them across tokens, overlooking their unequal contributions to the final outcome. On-policy self-distillation (OPSD) instead provides dense distributional supervision by minimizing the forward KL divergence between an unprivileged policy and a privileged self-teacher, implicitly assuming that the resulting likelihood shifts encode reliable answer-aligned information. We ","authors_text":"Qiangqiang He, Zhongheng Wu, Zijian Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:03:33Z","title":"Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27888","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":"sha256:253cbc11de0dd7a3f157b2526b5e7508a3c1f29cfdabef6661629cf5f55f42db","target":"record","created_at":"2026-07-31T01:34:34Z","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":"c936fe9a143a2130a48151f1935d0263d70983efd66b3dfa0d67d49c987e8b6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T09:03:33Z","title_canon_sha256":"605c0a3badf5c256b6c1f8481a7aa2bf07ced061fef454e684b6822d843ae9b8"},"schema_version":"1.0","source":{"id":"2607.27888","kind":"arxiv","version":1}},"canonical_sha256":"16758af08ceebff287d1ca737a3b8b2be68434e5cabcb78cb26cac193bb9105c","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16758af08ceebff287d1ca737a3b8b2be68434e5cabcb78cb26cac193bb9105c","first_computed_at":"2026-07-31T01:34:34.623236Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:34:34.623236Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:253cbc11de0dd7a3f157b2526b5e7508a3c1f29cfdabef6661629cf5f55f42db","sha256:7d026555226a108cb5321e415338b190b59c20f029616bf49c266a1bd12d8cde"],"state_sha256":"62036c00fd9ad951c0ecd78e30c35e83f82de29d85c1153bbae34a23a5f543b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W/1OdmO/I0iMjPdE8pwfA6ADPXZ1Rf+ms6ez4JFWmEpb2nRyjPv9opM6YnH1eK2FAoTGdrxdkISOHnFKlSvrCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:10:51.930365Z","bundle_sha256":"5c4c7b835eb5a0f477ae93da3ceef91be320c5ef30f89ed7f63db4d4281c74ca"}}