{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G5ZA4AWUYVUVZ6ZQ6TQ423M67R","short_pith_number":"pith:G5ZA4AWU","schema_version":"1.0","canonical_sha256":"37720e02d4c5695cfb30f4e1cd6d9efc5c0c816b60eed6886361888cf4eb114e","source":{"kind":"arxiv","id":"2605.11946","version":2},"attestation_state":"computed","paper":{"title":"Counterfactual Trace Auditing of LLM Agent Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Counterfactual Trace Auditing shows skills reshape LLM agent behavior in 522 specific ways even when pass rates change by less than one percent.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jinbo Liu, Li Li, Ryan A. Rossi, Xiaolin Zhou, Xiyang Hu","submitted_at":"2026-05-12T10:56:18Z","abstract_excerpt":"Large Language Model agents are increasingly augmented with agent skills. Current evaluation methods for skills remain limited. Most deployed benchmarks report only pass rate before and after a skill is attached, treating the skill as a black box change to agent behavior. We introduce Counterfactual Trace Auditing (CTA), a framework for measuring how a skill changes agent behavior. CTA pairs each with skill agent trace with a without skill counterpart on the same task, segments both traces into goal directed phases, aligns the phases, and emits structured Skill Influence Pattern (SIP) annotati"},"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":"2605.11946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T10:56:18Z","cross_cats_sorted":[],"title_canon_sha256":"11dc2659358d72a662e51468a6ff5521fee2d46ef44f79680d985008eaed3799","abstract_canon_sha256":"ca48521c969a2f9f7610fcbb3d91ae89a343431b732d80679848ab6bd2397466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:42.444916Z","signature_b64":"POSzpSEWrOz/ZJ/C04TE5JphG2EWH7h+v/h8aV7fUZLU0gNoUOCfLagzJYR8RkLal+ce6flqXJqeUdAhqYReAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37720e02d4c5695cfb30f4e1cd6d9efc5c0c816b60eed6886361888cf4eb114e","last_reissued_at":"2026-06-01T01:02:42.443559Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:42.443559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Trace Auditing of LLM Agent Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Counterfactual Trace Auditing shows skills reshape LLM agent behavior in 522 specific ways even when pass rates change by less than one percent.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jinbo Liu, Li Li, Ryan A. Rossi, Xiaolin Zhou, Xiyang Hu","submitted_at":"2026-05-12T10:56:18Z","abstract_excerpt":"Large Language Model agents are increasingly augmented with agent skills. Current evaluation methods for skills remain limited. Most deployed benchmarks report only pass rate before and after a skill is attached, treating the skill as a black box change to agent behavior. We introduce Counterfactual Trace Auditing (CTA), a framework for measuring how a skill changes agent behavior. CTA pairs each with skill agent trace with a without skill counterpart on the same task, segments both traces into goal directed phases, aligns the phases, and emits structured Skill Influence Pattern (SIP) annotati"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CTA identifies 522 SIP instances across the same paired traces, showing that the skills substantially reshape agent behavior even when pass rate is nearly unchanged.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That manual or automated segmentation of traces into goal-directed phases and their alignment produces unbiased, reproducible Skill Influence Pattern annotations that faithfully capture the causal effect of the skill.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CTA framework detects 522 skill influence patterns in LLM agent traces across 49 tasks where average pass rate shifts only +0.3%, exposing evaluation gaps in behavioral effects like template copying and excess planning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Counterfactual Trace Auditing shows skills reshape LLM agent behavior in 522 specific ways even when pass rates change by less than one percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a225b7133d890377415628f302549a25acfc254227473998c58c97cb07f18d14"},"source":{"id":"2605.11946","kind":"arxiv","version":2},"verdict":{"id":"7af122eb-ce8b-4e09-acf6-980166f4c1b6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T05:29:20.011378Z","strongest_claim":"CTA identifies 522 SIP instances across the same paired traces, showing that the skills substantially reshape agent behavior even when pass rate is nearly unchanged.","one_line_summary":"CTA framework detects 522 skill influence patterns in LLM agent traces across 49 tasks where average pass rate shifts only +0.3%, exposing evaluation gaps in behavioral effects like template copying and excess planning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That manual or automated segmentation of traces into goal-directed phases and their alignment produces unbiased, reproducible Skill Influence Pattern annotations that faithfully capture the causal effect of the skill.","pith_extraction_headline":"Counterfactual Trace Auditing shows skills reshape LLM agent behavior in 522 specific ways even when pass rates change by less than one percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11946/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-26T15:45:42.887690Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T18:01:27.061963Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T12:05:49.263997Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-20T03:22:00.224241Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0de92f3298b4c3a359a5e866ce0642933c106732a4875af5db4af720e5fb5633"},"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":"2605.11946","created_at":"2026-06-01T01:02:42.444135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11946v2","created_at":"2026-06-01T01:02:42.444135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11946","created_at":"2026-06-01T01:02:42.444135+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5ZA4AWUYVUV","created_at":"2026-06-01T01:02:42.444135+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5ZA4AWUYVUVZ6ZQ","created_at":"2026-06-01T01:02:42.444135+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5ZA4AWU","created_at":"2026-06-01T01:02:42.444135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.20631","citing_title":"Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R","json":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R.json","graph_json":"https://pith.science/api/pith-number/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/graph.json","events_json":"https://pith.science/api/pith-number/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/events.json","paper":"https://pith.science/paper/G5ZA4AWU"},"agent_actions":{"view_html":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R","download_json":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R.json","view_paper":"https://pith.science/paper/G5ZA4AWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11946&json=true","fetch_graph":"https://pith.science/api/pith-number/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/graph.json","fetch_events":"https://pith.science/api/pith-number/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/action/storage_attestation","attest_author":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/action/author_attestation","sign_citation":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/action/citation_signature","submit_replication":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/action/replication_record"}},"created_at":"2026-06-01T01:02:42.444135+00:00","updated_at":"2026-06-01T01:02:42.444135+00:00"}