{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2FL56AAQUA6FVA6M6SCXI3POL6","short_pith_number":"pith:2FL56AAQ","schema_version":"1.0","canonical_sha256":"d157df0010a03c5a83ccf485746dee5fbe0746e0afa8979acb03c139878ab06b","source":{"kind":"arxiv","id":"2605.14392","version":1},"attestation_state":"computed","paper":{"title":"Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dian Yu, Haitao Mi, Kishan Panaganti, Wenhao Yu, Yucheng Shi, Zhenwen Liang","submitted_at":"2026-05-14T05:14:45Z","abstract_excerpt":"We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In zero-data reasoning RL, this reframes self-improvement from a data-generation loop into an environment-construction loop, where each artifact is a reusable executable object that samples instances, computes references, and scores responses. Whether this vision sustains improvement hinges on a single property: the environments must exhibit stable solve--verify asymmetry, the model must be able to write an oracle once t"},"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":"2605.14392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T05:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"10fbd2ec6de1de6ace5123e972aed6682348241f61dc87e6b1679bf0bf0e1efc","abstract_canon_sha256":"9ba03b48dcda9692c6113d3355012a2f67f91a1707b505c8ab957b7600d482e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.603471Z","signature_b64":"oIPgalEY4sRsWekxwGmub0t4sdiyFeIv77S9qRNvCQnslT2kGGvVepOvgMWE40HiH+SBwLfNugdiiO96E7KVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d157df0010a03c5a83ccf485746dee5fbe0746e0afa8979acb03c139878ab06b","last_reissued_at":"2026-05-17T23:39:07.602841Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.602841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dian Yu, Haitao Mi, Kishan Panaganti, Wenhao Yu, Yucheng Shi, Zhenwen Liang","submitted_at":"2026-05-14T05:14:45Z","abstract_excerpt":"We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In zero-data reasoning RL, this reframes self-improvement from a data-generation loop into an environment-construction loop, where each artifact is a reusable executable object that samples instances, computes references, and scores responses. Whether this vision sustains improvement hinges on a single property: the environments must exhibit stable solve--verify asymmetry, the model must be able to write an oracle once t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14392","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":""},"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":"2605.14392","created_at":"2026-05-17T23:39:07.602920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14392v1","created_at":"2026-05-17T23:39:07.602920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14392","created_at":"2026-05-17T23:39:07.602920+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FL56AAQUA6F","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FL56AAQUA6FVA6M","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FL56AAQ","created_at":"2026-05-18T12:33:37.589309+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/2FL56AAQUA6FVA6M6SCXI3POL6","json":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6.json","graph_json":"https://pith.science/api/pith-number/2FL56AAQUA6FVA6M6SCXI3POL6/graph.json","events_json":"https://pith.science/api/pith-number/2FL56AAQUA6FVA6M6SCXI3POL6/events.json","paper":"https://pith.science/paper/2FL56AAQ"},"agent_actions":{"view_html":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6","download_json":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6.json","view_paper":"https://pith.science/paper/2FL56AAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14392&json=true","fetch_graph":"https://pith.science/api/pith-number/2FL56AAQUA6FVA6M6SCXI3POL6/graph.json","fetch_events":"https://pith.science/api/pith-number/2FL56AAQUA6FVA6M6SCXI3POL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6/action/storage_attestation","attest_author":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6/action/author_attestation","sign_citation":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6/action/citation_signature","submit_replication":"https://pith.science/pith/2FL56AAQUA6FVA6M6SCXI3POL6/action/replication_record"}},"created_at":"2026-05-17T23:39:07.602920+00:00","updated_at":"2026-05-17T23:39:07.602920+00:00"}