{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VRPQEFPY6NBPXH3TPMSFNGW5F2","short_pith_number":"pith:VRPQEFPY","schema_version":"1.0","canonical_sha256":"ac5f0215f8f342fb9f737b24569add2e8e35018ea7628b6487dbba72f2435250","source":{"kind":"arxiv","id":"2602.01244","version":3},"attestation_state":"computed","paper":{"title":"Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Dai, Chenghua Lin, Jian Yang, Mingjie Tang, Riza Batista-Navarro, Siwei Wu, Wei Zhang, Xian Yang, Yang Wang, Yizhi Li, Yuyang Song","submitted_at":"2026-02-01T14:09:23Z","abstract_excerpt":"Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. However, constructing such data at scale remains challenging due to two key requirements: \\textbf{\\emph{Executability}}, since each instance requires a suitable and often distinct Docker environment; and \\textbf{\\emph{Verifiability}}, because heterogeneous task outputs preclude unified, standardized verification. To address these challenges, we propose \\textbf{TerminalTraj}, a scalable pipeline that (i) filters high-q"},"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":"2602.01244","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-01T14:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"ed1a6432154a039bee98a117a7f077741dad0cb0f1a8a99bceab3205b2de0693","abstract_canon_sha256":"5a2fa6d2a56400ae22bfc5c5441a0a6c8be1b06bac374e1be03fcddabdaa8d7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:18:26.778592Z","signature_b64":"6UGC7KgR8+MoRXokcDVraGfDQmWYKvSKuqwId2nHVzIvqc3d3ftQ9Wdp5cmNEIyJhsAgMz1ZweTmlM3mCviJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac5f0215f8f342fb9f737b24569add2e8e35018ea7628b6487dbba72f2435250","last_reissued_at":"2026-07-20T01:18:26.777603Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:18:26.777603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Dai, Chenghua Lin, Jian Yang, Mingjie Tang, Riza Batista-Navarro, Siwei Wu, Wei Zhang, Xian Yang, Yang Wang, Yizhi Li, Yuyang Song","submitted_at":"2026-02-01T14:09:23Z","abstract_excerpt":"Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. However, constructing such data at scale remains challenging due to two key requirements: \\textbf{\\emph{Executability}}, since each instance requires a suitable and often distinct Docker environment; and \\textbf{\\emph{Verifiability}}, because heterogeneous task outputs preclude unified, standardized verification. To address these challenges, we propose \\textbf{TerminalTraj}, a scalable pipeline that (i) filters high-q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01244","kind":"arxiv","version":3},"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/2602.01244/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":"2602.01244","created_at":"2026-07-20T01:18:26.778075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01244v3","created_at":"2026-07-20T01:18:26.778075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01244","created_at":"2026-07-20T01:18:26.778075+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRPQEFPY6NBP","created_at":"2026-07-20T01:18:26.778075+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRPQEFPY6NBPXH3T","created_at":"2026-07-20T01:18:26.778075+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRPQEFPY","created_at":"2026-07-20T01:18:26.778075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2606.23321","citing_title":"Tmax: A simple recipe for terminal agents","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22883","citing_title":"CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03461","citing_title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29559","citing_title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22535","citing_title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17745","citing_title":"HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2","json":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2.json","graph_json":"https://pith.science/api/pith-number/VRPQEFPY6NBPXH3TPMSFNGW5F2/graph.json","events_json":"https://pith.science/api/pith-number/VRPQEFPY6NBPXH3TPMSFNGW5F2/events.json","paper":"https://pith.science/paper/VRPQEFPY"},"agent_actions":{"view_html":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2","download_json":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2.json","view_paper":"https://pith.science/paper/VRPQEFPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01244&json=true","fetch_graph":"https://pith.science/api/pith-number/VRPQEFPY6NBPXH3TPMSFNGW5F2/graph.json","fetch_events":"https://pith.science/api/pith-number/VRPQEFPY6NBPXH3TPMSFNGW5F2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2/action/storage_attestation","attest_author":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2/action/author_attestation","sign_citation":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2/action/citation_signature","submit_replication":"https://pith.science/pith/VRPQEFPY6NBPXH3TPMSFNGW5F2/action/replication_record"}},"created_at":"2026-07-20T01:18:26.778075+00:00","updated_at":"2026-07-20T01:18:26.778075+00:00"}