{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NGOF4PL2F3D2A6PKWIK3SDBTNR","short_pith_number":"pith:NGOF4PL2","schema_version":"1.0","canonical_sha256":"699c5e3d7a2ec7a079eab215b90c336c4e80d97be807fe947706c82f336c822b","source":{"kind":"arxiv","id":"2607.07702","version":1},"attestation_state":"computed","paper":{"title":"From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyuan Yang, Jiahang Xu, Peng Cheng, Xuan Feng, Ying Chang, Yuqing Yang","submitted_at":"2026-07-08T17:57:27Z","abstract_excerpt":"The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to diagnose agent failures and improve agent policies. However, real execution traces are difficult to use directly for optimization: large trace collections are often redundant and heterogeneous, making optimization inefficient and prone to overfitting to low-value failures; meanwhile, each individual trajectory also contains many irrelevant steps, while naive context reduction methods such as truncation or sliding windows can discard causally imp"},"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":"2607.07702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T17:57:27Z","cross_cats_sorted":[],"title_canon_sha256":"4bc2e13f768cae0210a223de3ab4f1a37cbd85190840f4b1721722eb3d4272d4","abstract_canon_sha256":"bbb344a97b41a2b5d375c95cab06eed3638b46ec75485db005644add4e22ae34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:39.667416Z","signature_b64":"uVFqD6KlwirizMP/ScqrQcuTQvB22FkRqDR6joSs761TedGG7aoSeNr1jPhiSD2vQM0pfSOBULA0bymqp5kbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"699c5e3d7a2ec7a079eab215b90c336c4e80d97be807fe947706c82f336c822b","last_reissued_at":"2026-07-09T01:20:39.666988Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:39.666988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyuan Yang, Jiahang Xu, Peng Cheng, Xuan Feng, Ying Chang, Yuqing Yang","submitted_at":"2026-07-08T17:57:27Z","abstract_excerpt":"The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to diagnose agent failures and improve agent policies. However, real execution traces are difficult to use directly for optimization: large trace collections are often redundant and heterogeneous, making optimization inefficient and prone to overfitting to low-value failures; meanwhile, each individual trajectory also contains many irrelevant steps, while naive context reduction methods such as truncation or sliding windows can discard causally imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07702","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/2607.07702/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":"2607.07702","created_at":"2026-07-09T01:20:39.667044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07702v1","created_at":"2026-07-09T01:20:39.667044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07702","created_at":"2026-07-09T01:20:39.667044+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGOF4PL2F3D2","created_at":"2026-07-09T01:20:39.667044+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGOF4PL2F3D2A6PK","created_at":"2026-07-09T01:20:39.667044+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGOF4PL2","created_at":"2026-07-09T01:20:39.667044+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/NGOF4PL2F3D2A6PKWIK3SDBTNR","json":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR.json","graph_json":"https://pith.science/api/pith-number/NGOF4PL2F3D2A6PKWIK3SDBTNR/graph.json","events_json":"https://pith.science/api/pith-number/NGOF4PL2F3D2A6PKWIK3SDBTNR/events.json","paper":"https://pith.science/paper/NGOF4PL2"},"agent_actions":{"view_html":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR","download_json":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR.json","view_paper":"https://pith.science/paper/NGOF4PL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07702&json=true","fetch_graph":"https://pith.science/api/pith-number/NGOF4PL2F3D2A6PKWIK3SDBTNR/graph.json","fetch_events":"https://pith.science/api/pith-number/NGOF4PL2F3D2A6PKWIK3SDBTNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR/action/storage_attestation","attest_author":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR/action/author_attestation","sign_citation":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR/action/citation_signature","submit_replication":"https://pith.science/pith/NGOF4PL2F3D2A6PKWIK3SDBTNR/action/replication_record"}},"created_at":"2026-07-09T01:20:39.667044+00:00","updated_at":"2026-07-09T01:20:39.667044+00:00"}