{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TSH7XV3MT5ZHQFONHJSLOBWOKR","short_pith_number":"pith:TSH7XV3M","schema_version":"1.0","canonical_sha256":"9c8ffbd76c9f727815cd3a64b706ce5443263348f3ed222c20300ea9742efd69","source":{"kind":"arxiv","id":"2607.28037","version":1},"attestation_state":"computed","paper":{"title":"ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianing Wang, Junlin Liu, Linsen Guo, Xiaoyu Li, Xingchen Liu, Xingjian Wu, Xuezhi Cao, Xuhang Zhu, Xunliang Cai","submitted_at":"2026-07-30T11:18:47Z","abstract_excerpt":"As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks.\n  In this work, we present ClawTrack, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score). ClawTrack comprises 320 tasks across 8 domains with 25+ deterministic mock services. A Process Grader scores e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.28037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T11:18:47Z","cross_cats_sorted":[],"title_canon_sha256":"30ddf850e04b6c8ac89542215660c4ae7c9f38ab6dd862e1a939283bce40a45e","abstract_canon_sha256":"a9648ee5d23978cceec2768abc38df76e18f902affc498cee1c7eb577b0ce0b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8ffbd76c9f727815cd3a64b706ce5443263348f3ed222c20300ea9742efd69","last_reissued_at":"2026-07-31T01:35:27.543473Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:27.543473Z"},"graph_snapshot":{"paper":{"title":"ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianing Wang, Junlin Liu, Linsen Guo, Xiaoyu Li, Xingchen Liu, Xingjian Wu, Xuezhi Cao, Xuhang Zhu, Xunliang Cai","submitted_at":"2026-07-30T11:18:47Z","abstract_excerpt":"As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks.\n  In this work, we present ClawTrack, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score). ClawTrack comprises 320 tasks across 8 domains with 25+ deterministic mock services. A Process Grader scores e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28037","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.28037/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.28037","created_at":"2026-07-31T01:35:27.546679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28037v1","created_at":"2026-07-31T01:35:27.546679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28037","created_at":"2026-07-31T01:35:27.546679+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSH7XV3MT5ZH","created_at":"2026-07-31T01:35:27.546679+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSH7XV3MT5ZHQFON","created_at":"2026-07-31T01:35:27.546679+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSH7XV3M","created_at":"2026-07-31T01:35:27.546679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR","json":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR.json","graph_json":"https://pith.science/api/pith-number/TSH7XV3MT5ZHQFONHJSLOBWOKR/graph.json","events_json":"https://pith.science/api/pith-number/TSH7XV3MT5ZHQFONHJSLOBWOKR/events.json","paper":"https://pith.science/paper/TSH7XV3M"},"agent_actions":{"view_html":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR","download_json":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR.json","view_paper":"https://pith.science/paper/TSH7XV3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28037&json=true","fetch_graph":"https://pith.science/api/pith-number/TSH7XV3MT5ZHQFONHJSLOBWOKR/graph.json","fetch_events":"https://pith.science/api/pith-number/TSH7XV3MT5ZHQFONHJSLOBWOKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/action/storage_attestation","attest_author":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/action/author_attestation","sign_citation":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/action/citation_signature","submit_replication":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/action/replication_record"}},"created_at":"2026-07-31T01:35:27.546679+00:00","updated_at":"2026-07-31T01:35:27.546679+00:00"}