{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6F4AQ4XYZDQH3IUVKLFH74MP6E","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":"25d09316b50538233ca0b5df70bdc2290fdab185ed217289d9357378ab8bea16","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T12:43:12Z","title_canon_sha256":"6876da6031e80bd6c93f71818740378fa8c12f160768066462af6cbc8aefb55b"},"schema_version":"1.0","source":{"id":"2607.10738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10738","created_at":"2026-07-14T01:21:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10738v1","created_at":"2026-07-14T01:21:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10738","created_at":"2026-07-14T01:21:37Z"},{"alias_kind":"pith_short_12","alias_value":"6F4AQ4XYZDQH","created_at":"2026-07-14T01:21:37Z"},{"alias_kind":"pith_short_16","alias_value":"6F4AQ4XYZDQH3IUV","created_at":"2026-07-14T01:21:37Z"},{"alias_kind":"pith_short_8","alias_value":"6F4AQ4XY","created_at":"2026-07-14T01:21:37Z"}],"graph_snapshots":[{"event_id":"sha256:69883232d76dd84f6c815b1cf788f7720a7fbf10c0d512d1a4a41f3b57f87f79","target":"graph","created_at":"2026-07-14T01:21:37Z","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/2607.10738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks. However, we argue that current training paradigms harbor a critical vulnerability: they predominantly reward correct answers but fail to penalize fabricated ones when retrieval fails, thereby implicitly exacerbating hallucinations. To address this, we propose Abstention-Aware Reinforcement Learning (AWA-RL), which dynamically shapes the abstention reward utilizing the model's query-specific prior capabilit","authors_text":"Bei Chen, Chengen Huang, Fengji Zhang, Jacky Keung, Tianyu Fan, Xinyao Niu, Yuxiang Zheng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T12:43:12Z","title":"To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10738","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":"sha256:7a7bcba7b09bbb118275706a7a5ac15faf7602f525b00f107444b83149b2085f","target":"record","created_at":"2026-07-14T01:21:37Z","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":"25d09316b50538233ca0b5df70bdc2290fdab185ed217289d9357378ab8bea16","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-12T12:43:12Z","title_canon_sha256":"6876da6031e80bd6c93f71818740378fa8c12f160768066462af6cbc8aefb55b"},"schema_version":"1.0","source":{"id":"2607.10738","kind":"arxiv","version":1}},"canonical_sha256":"f1780872f8c8e07da29552ca7ff18ff12ad772c4eb5151c1a4ee8e595e8b5051","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1780872f8c8e07da29552ca7ff18ff12ad772c4eb5151c1a4ee8e595e8b5051","first_computed_at":"2026-07-14T01:21:37.543395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:37.543395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbnIH3MxzHTpJgj6bLreqfuJjmzOBFImLvxW5wNpxjPlor/sIsDSPeH95v94zYliW8AOBpVNOUkqDD+KwMXwCw==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:37.544222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a7bcba7b09bbb118275706a7a5ac15faf7602f525b00f107444b83149b2085f","sha256:69883232d76dd84f6c815b1cf788f7720a7fbf10c0d512d1a4a41f3b57f87f79"],"state_sha256":"ccc8a4c9f7802c1d9bfdde4155aaf7bf3acaa23abfc2c1b1a3007588081acb19"}