{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MH7VRS4NAGH2VH5M4L5KF5KS6M","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":"2b44808441cde4ff49544086ee2d0290a6dd0510ce0b952b5d882dcd0156898d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-21T11:14:33Z","title_canon_sha256":"2c4b06ef1ff02cae24e2e306340b64986ef75850b0962bd5aa2b107c71033322"},"schema_version":"1.0","source":{"id":"2607.18979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18979","created_at":"2026-07-22T01:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18979v1","created_at":"2026-07-22T01:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18979","created_at":"2026-07-22T01:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"MH7VRS4NAGH2","created_at":"2026-07-22T01:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"MH7VRS4NAGH2VH5M","created_at":"2026-07-22T01:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"MH7VRS4N","created_at":"2026-07-22T01:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:41e3f155728fbee965fb6051bf40f3c43120b9bf30cc0838c7ca2c1b4571e674","target":"graph","created_at":"2026-07-22T01:24:02Z","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/2607.18979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) excel at multi-step reasoning, yet current parallel reasoning approaches often fail to distinguish the contributions of individual reasoning paths. Many paths may be redundant, misleading, or even detrimental, but outcome-level rewards assign uniform reward, leading to ambiguous learning signals and unstable training. We propose Parallel Shapley, a reinforcement learning framework that attributes fine-grained, path-level contributions in multi-path reasoning. Treating each path as a player in a cooperative game, we leverage Shapley values to quantify marginal contr","authors_text":"Dengji Zhao, Haoyu Zhang, Miao Li, Tao Feng, Wentao Zhang, Xinke Jiang, Yuhan Pan, Yuxuan Cheng, Zhen Tao, Zhipeng Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-21T11:14:33Z","title":"Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18979","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":"sha256:8dd046560913a93cf7ac8e3ec36b4fec641e34a9edb0ac6b38ce74af969df1e9","target":"record","created_at":"2026-07-22T01:24:02Z","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":"2b44808441cde4ff49544086ee2d0290a6dd0510ce0b952b5d882dcd0156898d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-21T11:14:33Z","title_canon_sha256":"2c4b06ef1ff02cae24e2e306340b64986ef75850b0962bd5aa2b107c71033322"},"schema_version":"1.0","source":{"id":"2607.18979","kind":"arxiv","version":1}},"canonical_sha256":"61ff58cb8d018faa9face2faa2f552f32c98b3281e966a1e1f529cf644469f72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61ff58cb8d018faa9face2faa2f552f32c98b3281e966a1e1f529cf644469f72","first_computed_at":"2026-07-22T01:24:02.672402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:02.672402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xWsReiSs7YyPKn5DegJoRtnHYqiK+VkugOSk2AbvIDuJBEZOYGtNZC3KXNghVfKpf1rTSIYfe3LjJ65TW7BdDQ==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:02.673280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dd046560913a93cf7ac8e3ec36b4fec641e34a9edb0ac6b38ce74af969df1e9","sha256:41e3f155728fbee965fb6051bf40f3c43120b9bf30cc0838c7ca2c1b4571e674"],"state_sha256":"4257bf35d3dffce0cdf24e40e53698f2c8b05bd08b2ec54f7bce78bd657c9d67"}