{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YKXO6DESZESY3J2Q5353WP6UQE","short_pith_number":"pith:YKXO6DES","schema_version":"1.0","canonical_sha256":"c2aeef0c92c9258da750eefbbb3fd481371ebb244a01710e9b04bcd902633d55","source":{"kind":"arxiv","id":"2606.08346","version":1},"attestation_state":"computed","paper":{"title":"CATPO: Critique-Augmented Tree Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankur Dahiya, Ayush Singh, Umang Goyal","submitted_at":"2026-06-06T21:29:01Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving the reasoning capabilities of large language models (LLMs). Recent tree-based methods such as TreeRPO extend flat trajectory sampling with tree-structured rollouts to obtain dense, step-level reward signals without a separate process reward model. However, not all trees are equally informative: trees where all leaves succeed, all leaves fail, or the policy already predicts the reward distribution contribute little to gradient updates, wasting compute. We introduce CATPO (Critique-Augmented Tree P"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.08346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T21:29:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea5840c620e0418aab03d996302f89e49255fbd14553a1782afc8b5e89fbf2fb","abstract_canon_sha256":"f071edf2600a4e7a25f444fdd4887e42fc72f539637655a546d2f60ac2b5a4bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:34.250849Z","signature_b64":"Nu4D9vBP0SNzZXFiInxr/pxneVO0nmy3FBq9yl8KXr2iI96/uiDm236sGUaKYc+/zYB9hJC89IhkuheOqHN2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2aeef0c92c9258da750eefbbb3fd481371ebb244a01710e9b04bcd902633d55","last_reissued_at":"2026-06-09T01:05:34.250397Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:34.250397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CATPO: Critique-Augmented Tree Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankur Dahiya, Ayush Singh, Umang Goyal","submitted_at":"2026-06-06T21:29:01Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving the reasoning capabilities of large language models (LLMs). Recent tree-based methods such as TreeRPO extend flat trajectory sampling with tree-structured rollouts to obtain dense, step-level reward signals without a separate process reward model. However, not all trees are equally informative: trees where all leaves succeed, all leaves fail, or the policy already predicts the reward distribution contribute little to gradient updates, wasting compute. We introduce CATPO (Critique-Augmented Tree P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08346","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/2606.08346/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.08346","created_at":"2026-06-09T01:05:34.250457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08346v1","created_at":"2026-06-09T01:05:34.250457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08346","created_at":"2026-06-09T01:05:34.250457+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKXO6DESZESY","created_at":"2026-06-09T01:05:34.250457+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKXO6DESZESY3J2Q","created_at":"2026-06-09T01:05:34.250457+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKXO6DES","created_at":"2026-06-09T01:05:34.250457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE","json":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE.json","graph_json":"https://pith.science/api/pith-number/YKXO6DESZESY3J2Q5353WP6UQE/graph.json","events_json":"https://pith.science/api/pith-number/YKXO6DESZESY3J2Q5353WP6UQE/events.json","paper":"https://pith.science/paper/YKXO6DES"},"agent_actions":{"view_html":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE","download_json":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE.json","view_paper":"https://pith.science/paper/YKXO6DES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08346&json=true","fetch_graph":"https://pith.science/api/pith-number/YKXO6DESZESY3J2Q5353WP6UQE/graph.json","fetch_events":"https://pith.science/api/pith-number/YKXO6DESZESY3J2Q5353WP6UQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE/action/storage_attestation","attest_author":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE/action/author_attestation","sign_citation":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE/action/citation_signature","submit_replication":"https://pith.science/pith/YKXO6DESZESY3J2Q5353WP6UQE/action/replication_record"}},"created_at":"2026-06-09T01:05:34.250457+00:00","updated_at":"2026-06-09T01:05:34.250457+00:00"}