{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZYL2MQ34FJF4PDV5I2F5DP3DI7","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":"417109bfdc2b2ad2240274ee2a3d892d6303d9c727848744fbb0b3f81fb73e50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T06:58:54Z","title_canon_sha256":"caf2102f3b6053142719ff907f2117dfbe97c0517020fa6c9884423bb96eb346"},"schema_version":"1.0","source":{"id":"2606.03239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03239","created_at":"2026-06-03T01:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03239v1","created_at":"2026-06-03T01:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03239","created_at":"2026-06-03T01:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZYL2MQ34FJF4","created_at":"2026-06-03T01:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZYL2MQ34FJF4PDV5","created_at":"2026-06-03T01:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZYL2MQ34","created_at":"2026-06-03T01:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:84dcb0af8d79da08f94af3276639148812af360035aab93af79bd3d5ac31303c","target":"graph","created_at":"2026-06-03T01:05:35Z","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/2606.03239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups where all sampled trajectories share the same correctness, yielding zero within-group advantage and no gradient. Existing process supervision either trains a costly verifier or generates per-query rubrics that are inconsistent across queries and discarded after one use. We propose ARBOR (Adaptive Rubric Buffer for Online Reward), a reusable process-reward framework that maintains a rubric memory shared across queries. ","authors_text":"Chengfu Huo, Liang Ding, Longxiang Zhang, Shaoxiong Zhan, Shu-Tao Xia, Tao Dai, Wen Huang, Xin Shan, Xintong Wang, Zheng Liu, Zhiang Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T06:58:54Z","title":"ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03239","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":"sha256:15007df86686ad09b1bf6b18b2128895d3ada0774ffe9ee74774b33e3e9437b0","target":"record","created_at":"2026-06-03T01:05:35Z","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":"417109bfdc2b2ad2240274ee2a3d892d6303d9c727848744fbb0b3f81fb73e50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T06:58:54Z","title_canon_sha256":"caf2102f3b6053142719ff907f2117dfbe97c0517020fa6c9884423bb96eb346"},"schema_version":"1.0","source":{"id":"2606.03239","kind":"arxiv","version":1}},"canonical_sha256":"ce17a6437c2a4bc78ebd468bd1bf6347f921231d507229e4e0ede542c69d6c1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce17a6437c2a4bc78ebd468bd1bf6347f921231d507229e4e0ede542c69d6c1f","first_computed_at":"2026-06-03T01:05:35.859905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:35.859905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lBQ1KlO6gGVREjv77Px76LxSrPAZtBDtu2RK7yvfR6e6poF6aIJG8eU5BEiQOj1mdvjCCGR1MhuhpkODnIF1Cg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:35.860332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15007df86686ad09b1bf6b18b2128895d3ada0774ffe9ee74774b33e3e9437b0","sha256:84dcb0af8d79da08f94af3276639148812af360035aab93af79bd3d5ac31303c"],"state_sha256":"e9f181f226c8a01240c2d16a63afd8887e986f9a28508f3238055fd116d957bb"}