{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G5ZA4AWUYVUVZ6ZQ6TQ423M67R","short_pith_number":"pith:G5ZA4AWU","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"},"canonical_sha256":"37720e02d4c5695cfb30f4e1cd6d9efc5c0c816b60eed6886361888cf4eb114e","source":{"kind":"arxiv","id":"2605.11946","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11946","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11946v2","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11946","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"pith_short_12","alias_value":"G5ZA4AWUYVUV","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"pith_short_16","alias_value":"G5ZA4AWUYVUVZ6ZQ","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"pith_short_8","alias_value":"G5ZA4AWU","created_at":"2026-06-01T01:02:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G5ZA4AWUYVUVZ6ZQ6TQ423M67R","target":"record","payload":{"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"},"canonical_sha256":"37720e02d4c5695cfb30f4e1cd6d9efc5c0c816b60eed6886361888cf4eb114e","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"},"source_kind":"arxiv","source_id":"2605.11946","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hhFI5egMlpEENffrMuRVFKYsNq0rKXlUwLEOUKZb07KmNQiZhzdfO0qb4n4VgB3e8qyef9Zw4fbOQkpOz6liBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T12:23:11.007877Z"},"content_sha256":"7e135adeafb968c262b8857af9a2676cbd7a72884667fd2362a33fb6e4438224","schema_version":"1.0","event_id":"sha256:7e135adeafb968c262b8857af9a2676cbd7a72884667fd2362a33fb6e4438224"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G5ZA4AWUYVUVZ6ZQ6TQ423M67R","target":"graph","payload":{"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"},"verdict_id":"7af122eb-ce8b-4e09-acf6-980166f4c1b6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubz0NhyCmFwDCPQJua7IFGCPwNONGtr/zyxb5QIZmi8OI8Pmv1GVr/cbVSjkv4oUVJkUcQJyKQ9S/2A1Ba8YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T12:23:11.008373Z"},"content_sha256":"f86dfad342eb6c4caa1f4867cb7ae03d8959b7a898ba7381ab08d3e380b51236","schema_version":"1.0","event_id":"sha256:f86dfad342eb6c4caa1f4867cb7ae03d8959b7a898ba7381ab08d3e380b51236"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/bundle.json","state_url":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/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":"2026-06-29T12:23:11Z","links":{"resolver":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R","bundle":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/bundle.json","state":"https://pith.science/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5ZA4AWUYVUVZ6ZQ6TQ423M67R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G5ZA4AWUYVUVZ6ZQ6TQ423M67R","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":"ca48521c969a2f9f7610fcbb3d91ae89a343431b732d80679848ab6bd2397466","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T10:56:18Z","title_canon_sha256":"11dc2659358d72a662e51468a6ff5521fee2d46ef44f79680d985008eaed3799"},"schema_version":"1.0","source":{"id":"2605.11946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11946","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11946v2","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11946","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"pith_short_12","alias_value":"G5ZA4AWUYVUV","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"pith_short_16","alias_value":"G5ZA4AWUYVUVZ6ZQ","created_at":"2026-06-01T01:02:42Z"},{"alias_kind":"pith_short_8","alias_value":"G5ZA4AWU","created_at":"2026-06-01T01:02:42Z"}],"graph_snapshots":[{"event_id":"sha256:f86dfad342eb6c4caa1f4867cb7ae03d8959b7a898ba7381ab08d3e380b51236","target":"graph","created_at":"2026-06-01T01:02:42Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Counterfactual Trace Auditing shows skills reshape LLM agent behavior in 522 specific ways even when pass rates change by less than one percent."}],"snapshot_sha256":"a225b7133d890377415628f302549a25acfc254227473998c58c97cb07f18d14"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.11946/integrity.json","findings":[],"snapshot_sha256":"0de92f3298b4c3a359a5e866ce0642933c106732a4875af5db4af720e5fb5633","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jinbo Liu, Li Li, Ryan A. Rossi, Xiaolin Zhou, Xiyang Hu","cross_cats":[],"headline":"Counterfactual Trace Auditing shows skills reshape LLM agent behavior in 522 specific ways even when pass rates change by less than one percent.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T10:56:18Z","title":"Counterfactual Trace Auditing of LLM Agent Skills"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11946","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T05:29:20.011378Z","id":"7af122eb-ce8b-4e09-acf6-980166f4c1b6","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"7af122eb-ce8b-4e09-acf6-980166f4c1b6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e135adeafb968c262b8857af9a2676cbd7a72884667fd2362a33fb6e4438224","target":"record","created_at":"2026-06-01T01:02:42Z","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":"ca48521c969a2f9f7610fcbb3d91ae89a343431b732d80679848ab6bd2397466","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T10:56:18Z","title_canon_sha256":"11dc2659358d72a662e51468a6ff5521fee2d46ef44f79680d985008eaed3799"},"schema_version":"1.0","source":{"id":"2605.11946","kind":"arxiv","version":2}},"canonical_sha256":"37720e02d4c5695cfb30f4e1cd6d9efc5c0c816b60eed6886361888cf4eb114e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37720e02d4c5695cfb30f4e1cd6d9efc5c0c816b60eed6886361888cf4eb114e","first_computed_at":"2026-06-01T01:02:42.443559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:42.443559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"POSzpSEWrOz/ZJ/C04TE5JphG2EWH7h+v/h8aV7fUZLU0gNoUOCfLagzJYR8RkLal+ce6flqXJqeUdAhqYReAg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:42.444916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e135adeafb968c262b8857af9a2676cbd7a72884667fd2362a33fb6e4438224","sha256:f86dfad342eb6c4caa1f4867cb7ae03d8959b7a898ba7381ab08d3e380b51236"],"state_sha256":"99506f958157e710f0184015294c8d4bbcab0b9911b3bc4dfff53d3f47d261ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8/svrAui6+vjYz416OZcYwMXQml9m6nTgbIydIgITVgFrJUeNli4S2tYHD/Z5WTh5kd596mjkTlqoayIn0G4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T12:23:11.010574Z","bundle_sha256":"0fe589aef39c681522551c69a99e44da417f5ddb0d66bbe08ff57eed07943494"}}