{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SGIXCAWFXAON2GDGCWOCOKMVMH","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":"5c2673c3022203c966059d64d2d72a4f0321088d908b7e17af32ab0a0b09e740","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T11:12:58Z","title_canon_sha256":"f57973817aff724c555f92e3e811ef87a3652c8554edd4b310de9455134b1cd5"},"schema_version":"1.0","source":{"id":"2606.10709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10709","created_at":"2026-06-10T01:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10709v1","created_at":"2026-06-10T01:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10709","created_at":"2026-06-10T01:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"SGIXCAWFXAON","created_at":"2026-06-10T01:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"SGIXCAWFXAON2GDG","created_at":"2026-06-10T01:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"SGIXCAWF","created_at":"2026-06-10T01:10:35Z"}],"graph_snapshots":[{"event_id":"sha256:386c358454bcc81e6991247410a0a1590b84db91e2876b06327ea2fb03f945bd","target":"graph","created_at":"2026-06-10T01:10:35Z","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/2606.10709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards. With these algorithms, a query contributes to parameter updates only when its rollout group mixes successes and failures; all-correct (too-easy) and all-incorrect (too-hard) groups are zero-variance and waste rollout cost. Existing approaches treat zero-variance as a static property and either discard or pre-filter such groups. We hypothesize and empirically validate that queries flip between zero-variance and signal-bearing states as the policy evolves during training. ","authors_text":"Bruno Martins, Chenyan Xiong, Jo\\~ao Coelho, Jo\\~ao Magalh\\~aes","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T11:12:58Z","title":"Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10709","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":"sha256:8ea72cb9e62b22c00685f74117906c24342b59603e0858c095208beb52cdbd5a","target":"record","created_at":"2026-06-10T01:10:35Z","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":"5c2673c3022203c966059d64d2d72a4f0321088d908b7e17af32ab0a0b09e740","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T11:12:58Z","title_canon_sha256":"f57973817aff724c555f92e3e811ef87a3652c8554edd4b310de9455134b1cd5"},"schema_version":"1.0","source":{"id":"2606.10709","kind":"arxiv","version":1}},"canonical_sha256":"91917102c5b81cdd1866159c27299561fdc3ffd674fdaf42e0281fc46d63f29e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91917102c5b81cdd1866159c27299561fdc3ffd674fdaf42e0281fc46d63f29e","first_computed_at":"2026-06-10T01:10:35.634984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:35.634984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MmdlTaV9NERUxpg2j7DmKg2akzJD95fR4ph9kscaoCsfgNwGBfAIbCUwTqeFF8QVBEbB7eQdM1R5LuRRyxHgCQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:35.635893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ea72cb9e62b22c00685f74117906c24342b59603e0858c095208beb52cdbd5a","sha256:386c358454bcc81e6991247410a0a1590b84db91e2876b06327ea2fb03f945bd"],"state_sha256":"c2f4b4adf1fc52af0c58daae0ab78c55d17f3354f9a8e3ada1572df99ac84e5c"}