{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZJANNJBFD5DNWTOM4HGYULHEFD","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":"a9af0d70757cee29ce9f7cc59785ebd2c06a62b5e1c749bb743584cfcb72aea2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:29Z","title_canon_sha256":"128806b972b05c45b2c4f051329c2341d319e4a2c4686fa3074805856d50b9f1"},"schema_version":"1.0","source":{"id":"2607.16244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16244","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16244v1","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16244","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZJANNJBFD5DN","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZJANNJBFD5DNWTOM","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZJANNJBF","created_at":"2026-07-21T00:20:07Z"}],"graph_snapshots":[{"event_id":"sha256:6eab46f32b44acea84a7a0cc687770e94cab101c7ce1444d752f6f3c9426b973","target":"graph","created_at":"2026-07-21T00:20:07Z","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/2607.16244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training multi-turn evidence-reading agents with outcome-only reinforcement learning is unstable because intermediate turns receive little direct credit. In HotpotQA experiments with Qwen2.5-3B-Instruct, GRPO initially improves (standard F1 0.430) but subsequently collapses to 100% format-violating outputs. Training-log diagnosis reveals a zero-advantage lock-in mechanism: all sampled trajectories receive the minimum format penalty (-2.0), group-relative advantages vanish, and the policy-gradient loss becomes zero--an optimization deadlock. We propose a variance-injection strategy: by assignin","authors_text":"Hao Dou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:29Z","title":"CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16244","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":"sha256:39592e91a4349dd00d2d2014b6472b9e40749a8ad26f8861a89204e84e88937f","target":"record","created_at":"2026-07-21T00:20:07Z","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":"a9af0d70757cee29ce9f7cc59785ebd2c06a62b5e1c749bb743584cfcb72aea2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T11:50:29Z","title_canon_sha256":"128806b972b05c45b2c4f051329c2341d319e4a2c4686fa3074805856d50b9f1"},"schema_version":"1.0","source":{"id":"2607.16244","kind":"arxiv","version":1}},"canonical_sha256":"ca40d6a4251f46db4dcce1cd8a2ce428d0b8fe2f23dfb7fe9b70f6fb8603c9c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca40d6a4251f46db4dcce1cd8a2ce428d0b8fe2f23dfb7fe9b70f6fb8603c9c4","first_computed_at":"2026-07-21T00:20:07.845381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:07.845381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cCLw/8PueICiTw9B9xFNaq4+3gMaC8jYdnY6xVmN0t1ow8Jwsfx+v+v7VsFPo4M3piFCi+PcFpJ4t5ufHsFYCg==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:07.846259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39592e91a4349dd00d2d2014b6472b9e40749a8ad26f8861a89204e84e88937f","sha256:6eab46f32b44acea84a7a0cc687770e94cab101c7ce1444d752f6f3c9426b973"],"state_sha256":"ee4f7a95474269e8b725663d8a7f4b56d0b119444a8315d9a60c3a1bed75f02b"}