{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CMAI2WD4QYL26H3LIHWGXJ7HUB","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":"7253b01d916f719ce5eeae63719b83bbcaa01320208e7572a10d091dcd0911b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T07:44:24Z","title_canon_sha256":"5b88aeff40020150d1fd45541d40ae090077415f50703a4ed328b37b93c97d9a"},"schema_version":"1.0","source":{"id":"2606.01830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01830","created_at":"2026-06-02T02:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01830v1","created_at":"2026-06-02T02:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01830","created_at":"2026-06-02T02:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"CMAI2WD4QYL2","created_at":"2026-06-02T02:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"CMAI2WD4QYL26H3L","created_at":"2026-06-02T02:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"CMAI2WD4","created_at":"2026-06-02T02:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:370f32120ec4331dc4a8431addeb8d4767e1e0f48501e1f2eaaa792889af21c0","target":"graph","created_at":"2026-06-02T02:04:58Z","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/2606.01830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent LLM search agents use reinforcement learning with verifiable rewards (RLVR) to learn search-augmented reasoning from outcome rewards. On hard problems, these agents rarely sample end-to-end successful rollouts, leaving outcome-only RLVR with few positive-reward trajectories. We argue that improving learning on such problems requires additional guidance during training, and RLVR already contains verifier-side information that can provide it. This information can identify errors or omissions in the agent's submitted answer and guide revision within the rollout. We propose a training-time ","authors_text":"Bin Chen, Chonghan Liu, Xin Liao, Xinye Liao, Yiming Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T07:44:24Z","title":"CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01830","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":"sha256:3c84b5063919d11238114ae869f74f2ef96906e7e8e075fefe4dfe0af7387212","target":"record","created_at":"2026-06-02T02:04:58Z","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":"7253b01d916f719ce5eeae63719b83bbcaa01320208e7572a10d091dcd0911b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T07:44:24Z","title_canon_sha256":"5b88aeff40020150d1fd45541d40ae090077415f50703a4ed328b37b93c97d9a"},"schema_version":"1.0","source":{"id":"2606.01830","kind":"arxiv","version":1}},"canonical_sha256":"13008d587c8617af1f6b41ec6ba7e7a07287ab60ea8b324df3866a82eb2b5e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13008d587c8617af1f6b41ec6ba7e7a07287ab60ea8b324df3866a82eb2b5e42","first_computed_at":"2026-06-02T02:04:58.000546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:58.000546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdbqlnPn5JSPurOv19qkgMXMzLnglguqJZHUIKVbole5WMqQUzyKEsVke2WLAXlx/Y8lT8uGJCLxPwelHXhKAg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:58.000917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c84b5063919d11238114ae869f74f2ef96906e7e8e075fefe4dfe0af7387212","sha256:370f32120ec4331dc4a8431addeb8d4767e1e0f48501e1f2eaaa792889af21c0"],"state_sha256":"40669958e22fe82ba99665938496955585ff02deeffdc8191b31935b10add4fc"}