{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YMV7HAO3KGQ6SJ2YUIUCPYZKKU","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":"93363cb2a2beafb6cd17d82eff26dc18cf8b3779177c0582ddb87897118ecb87","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-17T08:30:50Z","title_canon_sha256":"758d75a3c59079e0d1ba6c19499b597bd33189c6f38511b6d1b73fe7ebe65c6a"},"schema_version":"1.0","source":{"id":"2601.11960","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.11960","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2601.11960v3","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11960","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"YMV7HAO3KGQ6","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"YMV7HAO3KGQ6SJ2Y","created_at":"2026-07-07T01:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"YMV7HAO3","created_at":"2026-07-07T01:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:fb38f13a0a1c91ea4db9b2ae479046f16ddd74dad3049c5c24fadd8346088b75","target":"graph","created_at":"2026-07-07T01:16:04Z","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/2601.11960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses. We argue that this is a misleading inductive bias: the optimization-optimal trajectory distribution favors informative gradients, whereas the inference-optimal response distribution emphasizes accuracy and consistency. Forcing both into a single policy entangles their gradients and suppresses exploration. We propose R$^2$PO (Residual Rollout Policy Optimization), which attaches a lightweight Residual Rollout-Hea","authors_text":"Bingbing Xu, Bin Xie, Dan Zhang, Huawei Shen, Jingchu Wang, Xiaoqian Sun, Yige Yuan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-17T08:30:50Z","title":"R$^2$PO: Decoupling Rollout and Inference Policies for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.11960","kind":"arxiv","version":3},"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":"sha256:48cea06f368cf8de42816a5914510394c6aeb1aae917ed2cb3e8d7cb7ad7498b","target":"record","created_at":"2026-07-07T01:16:04Z","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":"93363cb2a2beafb6cd17d82eff26dc18cf8b3779177c0582ddb87897118ecb87","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-17T08:30:50Z","title_canon_sha256":"758d75a3c59079e0d1ba6c19499b597bd33189c6f38511b6d1b73fe7ebe65c6a"},"schema_version":"1.0","source":{"id":"2601.11960","kind":"arxiv","version":3}},"canonical_sha256":"c32bf381db51a1e92758a22827e32a553f4e2dcb4dfd9fb66b20bad11d7cc465","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c32bf381db51a1e92758a22827e32a553f4e2dcb4dfd9fb66b20bad11d7cc465","first_computed_at":"2026-07-07T01:16:04.237060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:04.237060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ATkStdSWhZOxZlI6dhThKibcG84i8eHI8zp0kFh2wha2OfLpA6bnFC2/h8UTj+ub+l/ozEHMyMjYtal9oYi4CQ==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:04.238005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.11960","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48cea06f368cf8de42816a5914510394c6aeb1aae917ed2cb3e8d7cb7ad7498b","sha256:fb38f13a0a1c91ea4db9b2ae479046f16ddd74dad3049c5c24fadd8346088b75"],"state_sha256":"4e13311502c1f609c0bd6ac831afc39cc170c2bb759aa20bb4f91292b5b9d938"}