{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MXWJYBYRETJ465A6GXA3FOZJ6D","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9dfdff4b80c9984d8f4474d112ea88319c034ba251e86646b9999c6dcd0a3a9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T14:24:43Z","title_canon_sha256":"2671f032a60f8234d74c71f1801a3d82577003307d9a8e4fecc9b8288934cc3f"},"schema_version":"1.0","source":{"id":"2605.22535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22535","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22535v1","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22535","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"MXWJYBYRETJ4","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"MXWJYBYRETJ465A6","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"MXWJYBYR","created_at":"2026-05-22T01:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:8511555e565e96846d264ee594f9980f5f03a206578ec345b65ffe3654d0a989","target":"graph","created_at":"2026-05-22T01:04:56Z","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/2605.22535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from \"in-the-wild\" terminal recordings. Processing 80,870 terminal recordings, the engine yields a full benchmark of 1,530 validated tasks, spanning 18 real-world categories, ranging from short everyday operations to workflows exceeding 50 steps, and covering 1,280 unique commands. From these, we curate a Verified subset of 200 representative, manually reviewed tasks. Comprehensive benchmarking on TerminalWorld-Verified across eight frontier models and six agents reveals that ","authors_text":"Chao Peng, Earl T. Barr, Federica Sarro, Han Li, He Ye, Jiarui Hu, Mark Harman, Pengyu Zou, Peter O'Hearn, Xingyu Jiang, Zhaoyang Chu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T14:24:43Z","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22535","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":"sha256:16b21242067936990ca917cb1c8976a8c45e2263c34baca6b37f51832d5da916","target":"record","created_at":"2026-05-22T01:04:56Z","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":"9dfdff4b80c9984d8f4474d112ea88319c034ba251e86646b9999c6dcd0a3a9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T14:24:43Z","title_canon_sha256":"2671f032a60f8234d74c71f1801a3d82577003307d9a8e4fecc9b8288934cc3f"},"schema_version":"1.0","source":{"id":"2605.22535","kind":"arxiv","version":1}},"canonical_sha256":"65ec9c071124d3cf741e35c1b2bb29f0e5a52bbb2b381a7e938ff11afa3aee92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65ec9c071124d3cf741e35c1b2bb29f0e5a52bbb2b381a7e938ff11afa3aee92","first_computed_at":"2026-05-22T01:04:56.104569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:56.104569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AAMasywqKt5nrE/Q9xX+25VDD6niuNBsXjX9mMpewdhiemGit25nbOgLCxLq4D3JYO0YZcgOPrq3Qcbn2m9XCg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:56.105662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16b21242067936990ca917cb1c8976a8c45e2263c34baca6b37f51832d5da916","sha256:8511555e565e96846d264ee594f9980f5f03a206578ec345b65ffe3654d0a989","sha256:03034f03c01d72a4e114b181e41ae348e64221363f2b40652fb6e26b658db1c8"],"state_sha256":"8dfe61ac410a319b4c59f681ae350e67f8b5d2e065908ddbfa21b54b88247e19"}