{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YGNS2Q2LKLLE72YQEFMGOFVVYK","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":"4b18647ad0fd2021e24183ac7562c38f187e9d11e30b8db6cde82da82115e210","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T03:52:37Z","title_canon_sha256":"1bd77a69d866f6ba68bb23e2c07e37678ab63cfb29c47964ade4c167ce647753"},"schema_version":"1.0","source":{"id":"2608.05573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05573","created_at":"2026-08-07T00:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05573v1","created_at":"2026-08-07T00:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05573","created_at":"2026-08-07T00:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"YGNS2Q2LKLLE","created_at":"2026-08-07T00:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"YGNS2Q2LKLLE72YQ","created_at":"2026-08-07T00:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"YGNS2Q2L","created_at":"2026-08-07T00:49:48Z"}],"graph_snapshots":[{"event_id":"sha256:01cf798e14a9d4352251c0b22fcbb409c27b805b0bd139c4964b672b681dac47","target":"graph","created_at":"2026-08-07T00:49:48Z","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/2608.05573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents increasingly execute long-horizon tasks through tool use and environment interaction, shifting evaluation from final-response scoring to verification of complete executions. For skill-augmented agents, verification additionally requires the procedural knowledge encoded in task-time skills, because this knowledge indicates what evidence to inspect and which failures are task-critical. However, existing judge benchmarks often expose final responses or static trajectories, and rarely combine task-time skills with directly inspectable artifacts and environments. We therefore introduce S","authors_text":"Chenxi Zeng, Liuhaichen Yang, Ming Zhou, Yang Li, Zhi Han, Zihan Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T03:52:37Z","title":"SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05573","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:dd4680c4807624c59b6c94082b79a66f1c7129d03e93860255405865f6f90672","target":"record","created_at":"2026-08-07T00:49:48Z","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":"4b18647ad0fd2021e24183ac7562c38f187e9d11e30b8db6cde82da82115e210","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T03:52:37Z","title_canon_sha256":"1bd77a69d866f6ba68bb23e2c07e37678ab63cfb29c47964ade4c167ce647753"},"schema_version":"1.0","source":{"id":"2608.05573","kind":"arxiv","version":1}},"canonical_sha256":"c19b2d434b52d64feb1021586716b5c2bf1a550a36c193fb1604327ec791f059","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c19b2d434b52d64feb1021586716b5c2bf1a550a36c193fb1604327ec791f059","first_computed_at":"2026-08-07T00:49:48.614128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:49:48.614128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PMVQBDfghQTiEpci/EkbhBpzapxOSryc3m9vw4kH2EFI0S8/DOQaDXyhs5FhlpfVUDisKDs/n+t8AWLu1je5DQ==","signature_status":"signed_v1","signed_at":"2026-08-07T00:49:48.615528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd4680c4807624c59b6c94082b79a66f1c7129d03e93860255405865f6f90672","sha256:01cf798e14a9d4352251c0b22fcbb409c27b805b0bd139c4964b672b681dac47"],"state_sha256":"929ed1bc0af68523bccaba40859abccb9eb83dac502dd03f9d6c719155b835db"}