{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MXWJYBYRETJ465A6GXA3FOZJ6D","short_pith_number":"pith:MXWJYBYR","canonical_record":{"source":{"id":"2605.22535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T14:24:43Z","cross_cats_sorted":[],"title_canon_sha256":"2671f032a60f8234d74c71f1801a3d82577003307d9a8e4fecc9b8288934cc3f","abstract_canon_sha256":"9dfdff4b80c9984d8f4474d112ea88319c034ba251e86646b9999c6dcd0a3a9f"},"schema_version":"1.0"},"canonical_sha256":"65ec9c071124d3cf741e35c1b2bb29f0e5a52bbb2b381a7e938ff11afa3aee92","source":{"kind":"arxiv","id":"2605.22535","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MXWJYBYRETJ465A6GXA3FOZJ6D","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T14:24:43Z","cross_cats_sorted":[],"title_canon_sha256":"2671f032a60f8234d74c71f1801a3d82577003307d9a8e4fecc9b8288934cc3f","abstract_canon_sha256":"9dfdff4b80c9984d8f4474d112ea88319c034ba251e86646b9999c6dcd0a3a9f"},"schema_version":"1.0"},"canonical_sha256":"65ec9c071124d3cf741e35c1b2bb29f0e5a52bbb2b381a7e938ff11afa3aee92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:56.105662Z","signature_b64":"AAMasywqKt5nrE/Q9xX+25VDD6niuNBsXjX9mMpewdhiemGit25nbOgLCxLq4D3JYO0YZcgOPrq3Qcbn2m9XCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ec9c071124d3cf741e35c1b2bb29f0e5a52bbb2b381a7e938ff11afa3aee92","last_reissued_at":"2026-05-22T01:04:56.104569Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:56.104569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22535","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QkvwP/Q3SYQr0uQDktMbLZiyXEEI2nWVoodupeWmZq48hZH4xaRl5Bh4o+iyf1VY0PdJXrz8SaCblNY4bi2WCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:27:05.899680Z"},"content_sha256":"16b21242067936990ca917cb1c8976a8c45e2263c34baca6b37f51832d5da916","schema_version":"1.0","event_id":"sha256:16b21242067936990ca917cb1c8976a8c45e2263c34baca6b37f51832d5da916"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MXWJYBYRETJ465A6GXA3FOZJ6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-05-21T14:24:43Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22535","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/2605.22535/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQOmJSsHMR9ppszc1e3pK1N6JZy5x7IfuNYNBrgFZisT2dZygdQGYnFWI35hA9A+BJmpVHGqVeKIiiarQzx8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:27:05.900408Z"},"content_sha256":"8511555e565e96846d264ee594f9980f5f03a206578ec345b65ffe3654d0a989","schema_version":"1.0","event_id":"sha256:8511555e565e96846d264ee594f9980f5f03a206578ec345b65ffe3654d0a989"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:MXWJYBYRETJ465A6GXA3FOZJ6D","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TSE.2014.2372785.DeepSeek.Deepseek) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.1109/TSE. 2014.2372785. DeepSeek. Deepseek v4 preview release. https://api-docs.deepseek.com/news/news260424,","arxiv_id":"2605.22535","detector":"doi_compliance","evidence":{"ref_index":17,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.1109/TSE. 2014.2372785. DeepSeek. Deepseek v4 preview release. https://api-docs.deepseek.com/news/news260424,","reconstructed_doi":"10.1109/TSE.2014.2372785.DeepSeek.Deepseek"},"severity":"advisory","ref_index":17,"audited_at":"2026-05-22T05:59:54.747830Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TSE.2014.2372785.DeepSeek.Deepseek","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"de80eb486b8d29402ceb20cbc21b792d5fa17fa9107070e086fa9e03ea4a480b","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":6259,"payload_sha256":"bd0184d2b329895dee7a0a535da251cd524a75accd8a5e72ad3d5ce65e1a167a","signature_b64":"7iilgCS2kUpFtGdK0GxbUlUmHvszDxuX/zfUwjlAGcvkvsyRrCdzGcYLS3ymKTsqZFjyPk/puB6OQf0WGlxJBw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T06:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GXry7SvjMiLdB81kImdLel/UfL6S/zVl/0lI7Mi+HFYqhpHtHAntBUPpYpf1EIfgKKRvJWiuR2MLkOfjVcsiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:27:05.901966Z"},"content_sha256":"03034f03c01d72a4e114b181e41ae348e64221363f2b40652fb6e26b658db1c8","schema_version":"1.0","event_id":"sha256:03034f03c01d72a4e114b181e41ae348e64221363f2b40652fb6e26b658db1c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXWJYBYRETJ465A6GXA3FOZJ6D/bundle.json","state_url":"https://pith.science/pith/MXWJYBYRETJ465A6GXA3FOZJ6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXWJYBYRETJ465A6GXA3FOZJ6D/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":"2026-05-27T16:27:05Z","links":{"resolver":"https://pith.science/pith/MXWJYBYRETJ465A6GXA3FOZJ6D","bundle":"https://pith.science/pith/MXWJYBYRETJ465A6GXA3FOZJ6D/bundle.json","state":"https://pith.science/pith/MXWJYBYRETJ465A6GXA3FOZJ6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXWJYBYRETJ465A6GXA3FOZJ6D/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5PwMpHIgskbDpAF7ubTKusbK1G4sL9758VGmrB8iJX8VuRravVayKRHeWU1PmjRmLbPssohcPyiM7W1vEMNdAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T16:27:05.905237Z","bundle_sha256":"9e597f7a2cfc2178d158ad9550323ec5db23e5f7dac8785a1b99706d577e7b66"}}