{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MLFKAQMAZE45MHW6FGHQKZ2CCP","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":"012f9ec60945ee3573c7a94eb5746e600d3ef5fba066dc6d8fe2676fe402e47b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T01:26:16Z","title_canon_sha256":"e24eff13e24dd89753af7249181a7df59f66f032d218cc194459391f4ea7560d"},"schema_version":"1.0","source":{"id":"2508.07534","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07534","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07534v2","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07534","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"MLFKAQMAZE45","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"MLFKAQMAZE45MHW6","created_at":"2026-07-05T11:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"MLFKAQMA","created_at":"2026-07-05T11:54:50Z"}],"graph_snapshots":[{"event_id":"sha256:0b471a2fe72fa37c63784e686ada44b9fecf3985af3cfa1ffeb38d705708016a","target":"graph","created_at":"2026-07-05T11:54:50Z","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/2508.07534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditional RL approaches, RLVR leverages rule-based feedback to guide LLMs in generating and refining complex reasoning chains -- a process critically dependent on effective exploration strategies. While prior work has demonstrated RLVR's empirical success, the fundamental mechanisms governing LLMs' exploration behaviors remain underexplored. This technical report presents a systematic investigation of exploration capacities ","authors_text":"Beichen Zhang, Daixuan Cheng, Fei Bai, Jia Deng, Jie Chen, Ji-Rong Wen, Wayne Xin Zhao, Yanzipeng Gao, Yinqian Min, Zhipeng Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T01:26:16Z","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07534","kind":"arxiv","version":2},"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:a13c8c8ed5f1a4353989289a5f4cdfade59d60ce3113b47ecd86c7ca09cef870","target":"record","created_at":"2026-07-05T11:54:50Z","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":"012f9ec60945ee3573c7a94eb5746e600d3ef5fba066dc6d8fe2676fe402e47b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T01:26:16Z","title_canon_sha256":"e24eff13e24dd89753af7249181a7df59f66f032d218cc194459391f4ea7560d"},"schema_version":"1.0","source":{"id":"2508.07534","kind":"arxiv","version":2}},"canonical_sha256":"62caa04180c939d61ede298f05674213c89b17eddbbf3259ddf8da45da1fcdc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62caa04180c939d61ede298f05674213c89b17eddbbf3259ddf8da45da1fcdc7","first_computed_at":"2026-07-05T11:54:50.774164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:50.774164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"etggnVXNy8R5K3Lnfz7HrfaAznSjE7OmftLLLwO9qT4WeIptpKbAEkXXb9b9x8j8hkHFd66jzEc6sJ0ow4VLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:50.774639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07534","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a13c8c8ed5f1a4353989289a5f4cdfade59d60ce3113b47ecd86c7ca09cef870","sha256:0b471a2fe72fa37c63784e686ada44b9fecf3985af3cfa1ffeb38d705708016a"],"state_sha256":"855912f83cb075448da00b5e1eb58c3e437fad6556d81be14501f427417748e0"}