{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HOMYJXGNGZNTZFCGXSM4PVCTYO","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":"064cc2c2ca40f26cb2a0adb8ee89860a2444ad390ef315636c09e16ac2588136","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-15T16:13:58Z","title_canon_sha256":"df90b5355175f32d097f1108fe7e1c458c25f55a77a1c8b6a383a1fe15e87042"},"schema_version":"1.0","source":{"id":"2603.14465","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.14465","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2603.14465v2","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14465","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"HOMYJXGNGZNT","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"HOMYJXGNGZNTZFCG","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"HOMYJXGN","created_at":"2026-06-02T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:82e3d6cb051022be9175c72c5d579d33f7f0c97ac238bf55f3bd7bf728640367","target":"graph","created_at":"2026-06-02T02:04:52Z","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/2603.14465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce irreversible side effects, making accurate step-level verification critical. However, existing process-level benchmarks are predominantly confined to closed-world mathematical domains, failing to capture the dynamic and open-ended nature of tool execution. To bridge this gap, we introduce AgentProcessBench, the first benchmark dedicated to evaluating step-l","authors_text":"Haotian Chen, Jingwen Chen, Shengda Fan, Shenzhi Yang, Shuqi Ye, Wenkai Yang, Xin Cong, Xuyan Ye, Yankai Lin, Yiju Guo, Yupeng Huo, Zhi-Yuan Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-15T16:13:58Z","title":"AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14465","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":"sha256:852d0608abc9da5e89d23a12b5ec8117de0efbb138664c36d61c4d20d8fbe072","target":"record","created_at":"2026-06-02T02:04:52Z","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":"064cc2c2ca40f26cb2a0adb8ee89860a2444ad390ef315636c09e16ac2588136","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-03-15T16:13:58Z","title_canon_sha256":"df90b5355175f32d097f1108fe7e1c458c25f55a77a1c8b6a383a1fe15e87042"},"schema_version":"1.0","source":{"id":"2603.14465","kind":"arxiv","version":2}},"canonical_sha256":"3b9984dccd365b3c9446bc99c7d453c3a1296e53daa4150f0bd324b9e3653d08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b9984dccd365b3c9446bc99c7d453c3a1296e53daa4150f0bd324b9e3653d08","first_computed_at":"2026-06-02T02:04:52.331443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:52.331443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkLcW0m7q/mUMDH1NCIOZsCYYCat4cUE2S9SWrfmFG6vj7jtYeslRiBFB9478VPJpZ2c+3pokrTD0MVDpO/VCQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:52.331963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.14465","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:852d0608abc9da5e89d23a12b5ec8117de0efbb138664c36d61c4d20d8fbe072","sha256:82e3d6cb051022be9175c72c5d579d33f7f0c97ac238bf55f3bd7bf728640367"],"state_sha256":"e143beb7f1af2ed8a0807add3005f09ec6e7eb12d6d609a756fa526729f809d7"}