{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SMZBUIZVBXZWVEBTW2UZ55O6GP","short_pith_number":"pith:SMZBUIZV","schema_version":"1.0","canonical_sha256":"93321a23350df36a9033b6a99ef5de33e878bfbc348bd239253fb17d08531885","source":{"kind":"arxiv","id":"2606.10394","version":1},"attestation_state":"computed","paper":{"title":"STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohan Yu, Cao Liu, Jian Zhao, Kang Liu, Ke Zeng, Peiyu Wang, Pengfei Cao, Shiguang Guo, Sirui Liang, Wenxing Hu, Xunliang Cai","submitted_at":"2026-06-09T04:16:35Z","abstract_excerpt":"Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existing benchmarks still rely on sandboxed artifacts, static task design, and coarse scoring, which hinder scalability and limit progress toward reliable personal-agent evaluation. This paper introduces STAGE-Claw, an automated framework for building and evaluating realistic personal-agent scenarios in state-based personal-computing environments. Given a task hint, STAGE-Claw automatically creates and validates a realistic benchmark task with its env"},"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":"2606.10394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T04:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"462e0926e80e6db924cec5374e9a925fa3a08d67f39faa5d558fd6d3eb92894d","abstract_canon_sha256":"699d586603ffff29ade1c87b30cee879ad0428886b8b9238ed5bf007f155d104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:15.715003Z","signature_b64":"sgx8L0GjGp36EZAnuTaNfpNiyEV6N2Z9ladgLDvoKXL2TPsvlM9k/MQ6Jg9QqDT9OgPLvPnLL080xNtaSii2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93321a23350df36a9033b6a99ef5de33e878bfbc348bd239253fb17d08531885","last_reissued_at":"2026-06-10T01:10:15.714142Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:15.714142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohan Yu, Cao Liu, Jian Zhao, Kang Liu, Ke Zeng, Peiyu Wang, Pengfei Cao, Shiguang Guo, Sirui Liang, Wenxing Hu, Xunliang Cai","submitted_at":"2026-06-09T04:16:35Z","abstract_excerpt":"Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existing benchmarks still rely on sandboxed artifacts, static task design, and coarse scoring, which hinder scalability and limit progress toward reliable personal-agent evaluation. This paper introduces STAGE-Claw, an automated framework for building and evaluating realistic personal-agent scenarios in state-based personal-computing environments. Given a task hint, STAGE-Claw automatically creates and validates a realistic benchmark task with its env"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10394","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/2606.10394/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":"2606.10394","created_at":"2026-06-10T01:10:15.714265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10394v1","created_at":"2026-06-10T01:10:15.714265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10394","created_at":"2026-06-10T01:10:15.714265+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMZBUIZVBXZW","created_at":"2026-06-10T01:10:15.714265+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMZBUIZVBXZWVEBT","created_at":"2026-06-10T01:10:15.714265+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMZBUIZV","created_at":"2026-06-10T01:10:15.714265+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/SMZBUIZVBXZWVEBTW2UZ55O6GP","json":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP.json","graph_json":"https://pith.science/api/pith-number/SMZBUIZVBXZWVEBTW2UZ55O6GP/graph.json","events_json":"https://pith.science/api/pith-number/SMZBUIZVBXZWVEBTW2UZ55O6GP/events.json","paper":"https://pith.science/paper/SMZBUIZV"},"agent_actions":{"view_html":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP","download_json":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP.json","view_paper":"https://pith.science/paper/SMZBUIZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10394&json=true","fetch_graph":"https://pith.science/api/pith-number/SMZBUIZVBXZWVEBTW2UZ55O6GP/graph.json","fetch_events":"https://pith.science/api/pith-number/SMZBUIZVBXZWVEBTW2UZ55O6GP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP/action/storage_attestation","attest_author":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP/action/author_attestation","sign_citation":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP/action/citation_signature","submit_replication":"https://pith.science/pith/SMZBUIZVBXZWVEBTW2UZ55O6GP/action/replication_record"}},"created_at":"2026-06-10T01:10:15.714265+00:00","updated_at":"2026-06-10T01:10:15.714265+00:00"}