{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C27474G2G53T33SK5N64K5SP7C","short_pith_number":"pith:C27474G2","schema_version":"1.0","canonical_sha256":"16bfcff0da37773dee4aeb7dc5764ff880e8c2955422ab73b678cec93ec8e0fa","source":{"kind":"arxiv","id":"2602.11210","version":4},"attestation_state":"computed","paper":{"title":"SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Danlong Yuan, Dongyan Zhao, Huishuai Zhang, Wei Wu, Xueliang Zhao, Zhengren Wang","submitted_at":"2026-02-11T02:33:04Z","abstract_excerpt":"Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage overhead, slow environment setup, and require container-management privileges. We propose SWE-MiniSandbox, a lightweight, container-free method that enables scalable RL training of SWE agents without sacrificing isolation. Instead of relying on per-instance containers, SWE-MiniSandbox executes each task in an isolated workspace backed by kernel-level mechan"},"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":"2602.11210","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-11T02:33:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4dacc385b1caadfeb94d527b35d51ce2535180f61ec1d8848c0a75679852b1d6","abstract_canon_sha256":"16c360f0e40a557879c6ba4cea5052d3e88c5d84bc66d6cd40cb05d707b90483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:57.396537Z","signature_b64":"7rnSVF1d+dfv7PJcj4p7ZuYnXQvUnDDhlIvlA/UiBWvexzociBYfhjV+PrnD3QXFRhSQ2LQG0IRcbNXam9pECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16bfcff0da37773dee4aeb7dc5764ff880e8c2955422ab73b678cec93ec8e0fa","last_reissued_at":"2026-05-22T01:03:57.395600Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:57.395600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Danlong Yuan, Dongyan Zhao, Huishuai Zhang, Wei Wu, Xueliang Zhao, Zhengren Wang","submitted_at":"2026-02-11T02:33:04Z","abstract_excerpt":"Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage overhead, slow environment setup, and require container-management privileges. We propose SWE-MiniSandbox, a lightweight, container-free method that enables scalable RL training of SWE agents without sacrificing isolation. Instead of relying on per-instance containers, SWE-MiniSandbox executes each task in an isolated workspace backed by kernel-level mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11210","kind":"arxiv","version":4},"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/2602.11210/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":"2602.11210","created_at":"2026-05-22T01:03:57.395739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11210v4","created_at":"2026-05-22T01:03:57.395739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11210","created_at":"2026-05-22T01:03:57.395739+00:00"},{"alias_kind":"pith_short_12","alias_value":"C27474G2G53T","created_at":"2026-05-22T01:03:57.395739+00:00"},{"alias_kind":"pith_short_16","alias_value":"C27474G2G53T33SK","created_at":"2026-05-22T01:03:57.395739+00:00"},{"alias_kind":"pith_short_8","alias_value":"C27474G2","created_at":"2026-05-22T01:03:57.395739+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/C27474G2G53T33SK5N64K5SP7C","json":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C.json","graph_json":"https://pith.science/api/pith-number/C27474G2G53T33SK5N64K5SP7C/graph.json","events_json":"https://pith.science/api/pith-number/C27474G2G53T33SK5N64K5SP7C/events.json","paper":"https://pith.science/paper/C27474G2"},"agent_actions":{"view_html":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C","download_json":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C.json","view_paper":"https://pith.science/paper/C27474G2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11210&json=true","fetch_graph":"https://pith.science/api/pith-number/C27474G2G53T33SK5N64K5SP7C/graph.json","fetch_events":"https://pith.science/api/pith-number/C27474G2G53T33SK5N64K5SP7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C/action/storage_attestation","attest_author":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C/action/author_attestation","sign_citation":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C/action/citation_signature","submit_replication":"https://pith.science/pith/C27474G2G53T33SK5N64K5SP7C/action/replication_record"}},"created_at":"2026-05-22T01:03:57.395739+00:00","updated_at":"2026-05-22T01:03:57.395739+00:00"}