{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O4IXK4NV7MX3Y6IUBGD5KGKZPS","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":"5f25ac801be7c472c56868e3ed356cbe35ff29169d25acd5b2bededa487613fc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:00:54Z","title_canon_sha256":"f47f22ea0e97e9262c81b191ca456360d5cf8966b2133713cb0031e40a6eb36d"},"schema_version":"1.0","source":{"id":"2607.07976","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07976","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07976v1","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07976","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"O4IXK4NV7MX3","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"O4IXK4NV7MX3Y6IU","created_at":"2026-07-10T00:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"O4IXK4NV","created_at":"2026-07-10T00:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:37de4d0cdeb820fef8e2074bc03e02dd52240706b43f6b185f0738d97a8b36bd","target":"graph","created_at":"2026-07-10T00:19:06Z","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/2607.07976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rely on uniform credit assignment, broadcasting the same advantage to all tokens regardless of their differences. We identify a critical failure mode of this design, which we refer to as Positive-Credit Contamination: low-probability tail tokens that are contextually erroneous receive identical positive credit to plausible ones within the same trajectory, resulting in the indiscriminate reinforcement of flawed reasoning","authors_text":"Guanchu Wang, Hoang Anh Duy Le, Vladimir Braverman, Xiuyi Lou, Yu-Neng Chuang, Zhaozhuo Xu, Zicheng Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:00:54Z","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07976","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":"sha256:3bb26c7b4644519bd80db14d6a649f32574a477a52645613ce62703cddf29f12","target":"record","created_at":"2026-07-10T00:19:06Z","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":"5f25ac801be7c472c56868e3ed356cbe35ff29169d25acd5b2bededa487613fc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T23:00:54Z","title_canon_sha256":"f47f22ea0e97e9262c81b191ca456360d5cf8966b2133713cb0031e40a6eb36d"},"schema_version":"1.0","source":{"id":"2607.07976","kind":"arxiv","version":1}},"canonical_sha256":"77117571b5fb2fbc79140987d519597caf0770cd35e28c830d5d11a188f1ab75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77117571b5fb2fbc79140987d519597caf0770cd35e28c830d5d11a188f1ab75","first_computed_at":"2026-07-10T00:19:06.409946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T00:19:06.409946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4ltXZARSf3ge6ymmllN+ghftVPxM7YPlfGsVNrbFXBTvvLLhS7akyDRJLlYPiGKHAE/nwOw1km3d1/uPULLDA==","signature_status":"signed_v1","signed_at":"2026-07-10T00:19:06.410341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07976","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bb26c7b4644519bd80db14d6a649f32574a477a52645613ce62703cddf29f12","sha256:37de4d0cdeb820fef8e2074bc03e02dd52240706b43f6b185f0738d97a8b36bd"],"state_sha256":"f25e655a712c4d2fdf95208cbc2786bd3f29f5b905fa40b83b92b5a3deb2dc38"}