{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WLW2XT2UJNY7WMIKOBWMAK3A4K","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":"989ea236cc259111ce66523cdfcc05c24975c81677e8a42c031255a12f557f73","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:28:14Z","title_canon_sha256":"2b69cef081f93566af8f67d6d9208a8a6a9f6c9eb8c909dec677fc9a99290e8e"},"schema_version":"1.0","source":{"id":"2605.24547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24547","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24547v1","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24547","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"WLW2XT2UJNY7","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"WLW2XT2UJNY7WMIK","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"WLW2XT2U","created_at":"2026-05-26T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:9883a636d07fa477802891f28be1899ac73b7bdc669a7a23737d10edd2ced5b0","target":"graph","created_at":"2026-05-26T01:03:45Z","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/2605.24547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing line of work on RL with textual feedback, where a critic model generates natural language feedback to guide a reasoning model (the actor), augmenting scalar rewards with richer learning signals. However, existing methods typically treat feedback as fixed or auxiliary, which misses a key property: feedback should not merely be correct, but should improve the policy (actor model) when provided in context. This motivates a","authors_text":"Amrit Singh Bedi, Sidhaarth Sredharan, Souradip Chakraborty, Utsav Singh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:28:14Z","title":"RL with Learnable Textual Feedback: A Bilevel Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24547","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":"sha256:2e530ed2a6acb0d9789a2a654067be51aa326b6eeab378bd6644e8a32e799abd","target":"record","created_at":"2026-05-26T01:03:45Z","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":"989ea236cc259111ce66523cdfcc05c24975c81677e8a42c031255a12f557f73","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:28:14Z","title_canon_sha256":"2b69cef081f93566af8f67d6d9208a8a6a9f6c9eb8c909dec677fc9a99290e8e"},"schema_version":"1.0","source":{"id":"2605.24547","kind":"arxiv","version":1}},"canonical_sha256":"b2edabcf544b71fb310a706cc02b60e281016faad3ea16b9c06bceada364dde2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2edabcf544b71fb310a706cc02b60e281016faad3ea16b9c06bceada364dde2","first_computed_at":"2026-05-26T01:03:45.777480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:45.777480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bi+aErmJU/mcpLpcp3IUMWJ76sspgZ7snxdxRVKfhbA9oIpxf8sBIae+JSsvmyJornIWNKSa04Ckhzq0uahrBg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:45.778327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e530ed2a6acb0d9789a2a654067be51aa326b6eeab378bd6644e8a32e799abd","sha256:9883a636d07fa477802891f28be1899ac73b7bdc669a7a23737d10edd2ced5b0"],"state_sha256":"f8ae5793fcafe8d71412000e2556569b2311decda7074aa8ac05b0594edf4d75"}