{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TSH7XV3MT5ZHQFONHJSLOBWOKR","short_pith_number":"pith:TSH7XV3M","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"},"canonical_sha256":"9c8ffbd76c9f727815cd3a64b706ce5443263348f3ed222c20300ea9742efd69","source":{"kind":"arxiv","id":"2607.28037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28037","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28037v1","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28037","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"TSH7XV3MT5ZH","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"TSH7XV3MT5ZHQFON","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"TSH7XV3M","created_at":"2026-07-31T01:35:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TSH7XV3MT5ZHQFONHJSLOBWOKR","target":"record","payload":{"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"},"canonical_sha256":"9c8ffbd76c9f727815cd3a64b706ce5443263348f3ed222c20300ea9742efd69","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"},"source_kind":"arxiv","source_id":"2607.28037","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UONct3oWdUvTp8V1nJrUwBq1NYP1m6vfimYlekKwjwQm39TLO5BnvzHpMjGpReEG/Da/VQ6cwntjlfwK9H6uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:03:24.425266Z"},"content_sha256":"d58ce7efe655c1ec2d01b1fdbfd6d502a4475ffdd32c3d97b893c3137d909aab","schema_version":"1.0","event_id":"sha256:d58ce7efe655c1ec2d01b1fdbfd6d502a4475ffdd32c3d97b893c3137d909aab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TSH7XV3MT5ZHQFONHJSLOBWOKR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1AvEDgkD2/aItlCF0gZxfZo/ADc0tndIKFkVT/nZ/jCPjkT7GXrmn2Ck2YMUxR8DeIAwXkGLxJ06KSByqfmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:03:24.425748Z"},"content_sha256":"947ab70143fafd5a5ac6e5b541fdddfa9d2151d3b6736332a177454f2c1ef73e","schema_version":"1.0","event_id":"sha256:947ab70143fafd5a5ac6e5b541fdddfa9d2151d3b6736332a177454f2c1ef73e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/bundle.json","state_url":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T12:03:24Z","links":{"resolver":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR","bundle":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/bundle.json","state":"https://pith.science/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSH7XV3MT5ZHQFONHJSLOBWOKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TSH7XV3MT5ZHQFONHJSLOBWOKR","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":"a9648ee5d23978cceec2768abc38df76e18f902affc498cee1c7eb577b0ce0b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T11:18:47Z","title_canon_sha256":"30ddf850e04b6c8ac89542215660c4ae7c9f38ab6dd862e1a939283bce40a45e"},"schema_version":"1.0","source":{"id":"2607.28037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28037","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28037v1","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28037","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"pith_short_12","alias_value":"TSH7XV3MT5ZH","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"pith_short_16","alias_value":"TSH7XV3MT5ZHQFON","created_at":"2026-07-31T01:35:27Z"},{"alias_kind":"pith_short_8","alias_value":"TSH7XV3M","created_at":"2026-07-31T01:35:27Z"}],"graph_snapshots":[{"event_id":"sha256:947ab70143fafd5a5ac6e5b541fdddfa9d2151d3b6736332a177454f2c1ef73e","target":"graph","created_at":"2026-07-31T01:35:27Z","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/2607.28037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianing Wang, Junlin Liu, Linsen Guo, Xiaoyu Li, Xingchen Liu, Xingjian Wu, Xuezhi Cao, Xuhang Zhu, Xunliang Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T11:18:47Z","title":"ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28037","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:d58ce7efe655c1ec2d01b1fdbfd6d502a4475ffdd32c3d97b893c3137d909aab","target":"record","created_at":"2026-07-31T01:35:27Z","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":"a9648ee5d23978cceec2768abc38df76e18f902affc498cee1c7eb577b0ce0b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T11:18:47Z","title_canon_sha256":"30ddf850e04b6c8ac89542215660c4ae7c9f38ab6dd862e1a939283bce40a45e"},"schema_version":"1.0","source":{"id":"2607.28037","kind":"arxiv","version":1}},"canonical_sha256":"9c8ffbd76c9f727815cd3a64b706ce5443263348f3ed222c20300ea9742efd69","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c8ffbd76c9f727815cd3a64b706ce5443263348f3ed222c20300ea9742efd69","first_computed_at":"2026-07-31T01:35:27.543473Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:27.543473Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d58ce7efe655c1ec2d01b1fdbfd6d502a4475ffdd32c3d97b893c3137d909aab","sha256:947ab70143fafd5a5ac6e5b541fdddfa9d2151d3b6736332a177454f2c1ef73e"],"state_sha256":"012f2860f8c03fcdddb0a28f5339c7d3d83d1dd908697003cc0ba80d56afdf16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9V6s/MQCbpuW4Bb5/yaqmSZaGfW3QqGqI2Cx/lykHN2XaAk4rIh/Tj2jSLYRvXOalGGrh+lKRCSUltdtRkiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T12:03:24.429220Z","bundle_sha256":"050b202f22cd78dc99e11c786d7d3534c5dc969242fa366bb2a6dd754f58fdce"}}