{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YGNS2Q2LKLLE72YQEFMGOFVVYK","short_pith_number":"pith:YGNS2Q2L","schema_version":"1.0","canonical_sha256":"c19b2d434b52d64feb1021586716b5c2bf1a550a36c193fb1604327ec791f059","source":{"kind":"arxiv","id":"2608.05573","version":1},"attestation_state":"computed","paper":{"title":"SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenxi Zeng, Liuhaichen Yang, Ming Zhou, Yang Li, Zhi Han, Zihan Guo","submitted_at":"2026-08-06T03:52:37Z","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"},"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":"2608.05573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T03:52:37Z","cross_cats_sorted":[],"title_canon_sha256":"1bd77a69d866f6ba68bb23e2c07e37678ab63cfb29c47964ade4c167ce647753","abstract_canon_sha256":"4b18647ad0fd2021e24183ac7562c38f187e9d11e30b8db6cde82da82115e210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:49:48.615528Z","signature_b64":"PMVQBDfghQTiEpci/EkbhBpzapxOSryc3m9vw4kH2EFI0S8/DOQaDXyhs5FhlpfVUDisKDs/n+t8AWLu1je5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c19b2d434b52d64feb1021586716b5c2bf1a550a36c193fb1604327ec791f059","last_reissued_at":"2026-08-07T00:49:48.614128Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:49:48.614128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenxi Zeng, Liuhaichen Yang, Ming Zhou, Yang Li, Zhi Han, Zihan Guo","submitted_at":"2026-08-06T03:52:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05573","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/2608.05573/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":"2608.05573","created_at":"2026-08-07T00:49:48.615537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05573v1","created_at":"2026-08-07T00:49:48.615537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05573","created_at":"2026-08-07T00:49:48.615537+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGNS2Q2LKLLE","created_at":"2026-08-07T00:49:48.615537+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGNS2Q2LKLLE72YQ","created_at":"2026-08-07T00:49:48.615537+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGNS2Q2L","created_at":"2026-08-07T00:49:48.615537+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/YGNS2Q2LKLLE72YQEFMGOFVVYK","json":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK.json","graph_json":"https://pith.science/api/pith-number/YGNS2Q2LKLLE72YQEFMGOFVVYK/graph.json","events_json":"https://pith.science/api/pith-number/YGNS2Q2LKLLE72YQEFMGOFVVYK/events.json","paper":"https://pith.science/paper/YGNS2Q2L"},"agent_actions":{"view_html":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK","download_json":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK.json","view_paper":"https://pith.science/paper/YGNS2Q2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05573&json=true","fetch_graph":"https://pith.science/api/pith-number/YGNS2Q2LKLLE72YQEFMGOFVVYK/graph.json","fetch_events":"https://pith.science/api/pith-number/YGNS2Q2LKLLE72YQEFMGOFVVYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK/action/storage_attestation","attest_author":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK/action/author_attestation","sign_citation":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK/action/citation_signature","submit_replication":"https://pith.science/pith/YGNS2Q2LKLLE72YQEFMGOFVVYK/action/replication_record"}},"created_at":"2026-08-07T00:49:48.615537+00:00","updated_at":"2026-08-07T00:49:48.615537+00:00"}