{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C4II5D5D4TEO3KHZOFOZHJESGN","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":"4cafb4e901206f88e9d7d009ba496bff675dc95f76e93e2de0b1fb9656771eb1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:29:11Z","title_canon_sha256":"9782fc6a3437c8fa38eae55d16e339e4bc8294bdf9d93e7ba5599c5a1a3311b8"},"schema_version":"1.0","source":{"id":"2608.01822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01822","created_at":"2026-08-04T02:07:14Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01822v1","created_at":"2026-08-04T02:07:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01822","created_at":"2026-08-04T02:07:14Z"},{"alias_kind":"pith_short_12","alias_value":"C4II5D5D4TEO","created_at":"2026-08-04T02:07:14Z"},{"alias_kind":"pith_short_16","alias_value":"C4II5D5D4TEO3KHZ","created_at":"2026-08-04T02:07:14Z"},{"alias_kind":"pith_short_8","alias_value":"C4II5D5D","created_at":"2026-08-04T02:07:14Z"}],"graph_snapshots":[{"event_id":"sha256:7f9bde2edf2d6f3421feff32a136cc16275ed5d37ff71dc57c61cc53e53061e4","target":"graph","created_at":"2026-08-04T02:07:14Z","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/2608.01822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search tools effectively. Existing pipelines often depend on human-written tasks, expert demonstrations, or stronger teacher models. We present SearchMaster, a self-play framework that trains a single LLM from search tasks it generates, solves, and verifies in a local search environment. The key challenge is that self-generated tasks and rollouts can yield misleading signals: pseudo multi-hop questions, success-rate difficulty estimates that ignore search ","authors_text":"Jiaqi Wang, Nan Duan, Qiong Cao, Wentao Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:29:11Z","title":"SearchMaster: Grounded and Regulated Self-Play for Search Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01822","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":"sha256:4871a4126d8849413fd24d0e9990a33d37bc86b4378b94600de5e1b9b216273f","target":"record","created_at":"2026-08-04T02:07:14Z","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":"4cafb4e901206f88e9d7d009ba496bff675dc95f76e93e2de0b1fb9656771eb1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T07:29:11Z","title_canon_sha256":"9782fc6a3437c8fa38eae55d16e339e4bc8294bdf9d93e7ba5599c5a1a3311b8"},"schema_version":"1.0","source":{"id":"2608.01822","kind":"arxiv","version":1}},"canonical_sha256":"17108e8fa3e4c8eda8f9715d93a4923365e98ef05266d6d9700eea3c2f8f29bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17108e8fa3e4c8eda8f9715d93a4923365e98ef05266d6d9700eea3c2f8f29bc","first_computed_at":"2026-08-04T02:07:14.771269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:07:14.771269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yMt6RHsI4F+W2O+sPtmWJ+rN/LEcvWpkLYj0kGY5kcBF2dTeF8o+snB/g09KitiZu0pB3SWcZPsLCeWzo9MiDQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:07:14.773236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4871a4126d8849413fd24d0e9990a33d37bc86b4378b94600de5e1b9b216273f","sha256:7f9bde2edf2d6f3421feff32a136cc16275ed5d37ff71dc57c61cc53e53061e4"],"state_sha256":"6369f399c7b8a3da4b3ff925b2c7ff4461c475bdec17dfee91b3c380e2f6ca96"}