{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LJKOVZP6MDUJLQL2GSEOCIX653","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":"88d8671d2ff0ba888fddea4e87175a8ff8e498c5e4dd5fc09c594995eb27b140","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T08:28:10Z","title_canon_sha256":"37cffb8ee7a69d91136785b25f28fdf5ea9e094b4b9cd0fe4d22cc0e16bc2f5f"},"schema_version":"1.0","source":{"id":"2605.29584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29584","created_at":"2026-05-29T01:05:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29584v1","created_at":"2026-05-29T01:05:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29584","created_at":"2026-05-29T01:05:49Z"},{"alias_kind":"pith_short_12","alias_value":"LJKOVZP6MDUJ","created_at":"2026-05-29T01:05:49Z"},{"alias_kind":"pith_short_16","alias_value":"LJKOVZP6MDUJLQL2","created_at":"2026-05-29T01:05:49Z"},{"alias_kind":"pith_short_8","alias_value":"LJKOVZP6","created_at":"2026-05-29T01:05:49Z"}],"graph_snapshots":[{"event_id":"sha256:b89637bf7e6a89b851484636fd6d1d1eeae34542c1ef98861089f6ec8b28befd","target":"graph","created_at":"2026-05-29T01:05:49Z","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/2605.29584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe knowledge-base feedback, and eventually return an answer. However, current RL-based KBQA systems mainly optimize sparse rewards from the final answer, leaving intermediate action errors weakly supervised. This is especially limiting for logical-form annotated KBQA benchmarks: gold logical forms can be converted into executable action sequences, but existing pipelines use them mainly for warm-start data construction rather than for on-policy RL ","authors_text":"Bowen Song, Jianan Xie, Liang Wang, Qiang Liu, Shu Wu, Weiqiang Wang, Xin Sun, Zhongqi Chen, Zilei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T08:28:10Z","title":"GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29584","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:a12745b86e31f9575b4a18a4e50dbfb0ce1d673781ff9d9426169373ab664295","target":"record","created_at":"2026-05-29T01:05:49Z","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":"88d8671d2ff0ba888fddea4e87175a8ff8e498c5e4dd5fc09c594995eb27b140","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T08:28:10Z","title_canon_sha256":"37cffb8ee7a69d91136785b25f28fdf5ea9e094b4b9cd0fe4d22cc0e16bc2f5f"},"schema_version":"1.0","source":{"id":"2605.29584","kind":"arxiv","version":1}},"canonical_sha256":"5a54eae5fe60e895c17a3488e122feeeefcc17c7a10d2419fc1cac4cbfb39a26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a54eae5fe60e895c17a3488e122feeeefcc17c7a10d2419fc1cac4cbfb39a26","first_computed_at":"2026-05-29T01:05:49.076730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:49.076730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EUvC9UnCkbzG7zUj2T8bm8x7AQBSY9zMwEONvk2Y3gW8OvXjuElmMQiqERsb9WDYV6Xg8dPBYbsdIBCB1/m3Cg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:49.077677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a12745b86e31f9575b4a18a4e50dbfb0ce1d673781ff9d9426169373ab664295","sha256:b89637bf7e6a89b851484636fd6d1d1eeae34542c1ef98861089f6ec8b28befd"],"state_sha256":"846dcc95966fdfb0b30f879d156741657bd15bc113da3d6291ce9facf599cd9a"}