{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SKNZAYC57DXG45E6GZC5K5XWPU","short_pith_number":"pith:SKNZAYC5","schema_version":"1.0","canonical_sha256":"929b90605df8ee6e749e3645d576f67d0dd6bd36b45d396902cb29acbf393b87","source":{"kind":"arxiv","id":"2606.20657","version":1},"attestation_state":"computed","paper":{"title":"A-Evolve-Training: Autonomous Post-Training of a 30B Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bing He, Hanqing Lu, Yisi Sang, Zhan Shi","submitted_at":"2026-06-09T07:23:11Z","abstract_excerpt":"Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous system that runs this loop with no human in the loop, post-training a 30B Nemotron across four rounds over multiple weeks. The autonomously produced model reaches a held-out score of 0.86 against the top human submission's 0.87 on the public NVIDIA Nemotron-Reasoning Challenge leaderboard, placing 8th of ~4000 at the time of writing. More striking than the number: the loop detected that its own dev metric had stopped tr"},"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":"2606.20657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T07:23:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ebfa89656063db526894696ab283384b131bd6f8765ad5ed378565dca0bf809","abstract_canon_sha256":"445813fd7e329ee0a1a66b4965dee14cd2c3491a9e3314806d3d60c728e542b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:52.780376Z","signature_b64":"LIwFNc7YVGa1qozW8uAW/du3opFdEAxy3Mn0aqAfkxBq/TniiWCiEdvuPEmT4+T2pkblGnNve6OTyp84IL9UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"929b90605df8ee6e749e3645d576f67d0dd6bd36b45d396902cb29acbf393b87","last_reissued_at":"2026-06-23T00:11:52.779972Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:52.779972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A-Evolve-Training: Autonomous Post-Training of a 30B Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bing He, Hanqing Lu, Yisi Sang, Zhan Shi","submitted_at":"2026-06-09T07:23:11Z","abstract_excerpt":"Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous system that runs this loop with no human in the loop, post-training a 30B Nemotron across four rounds over multiple weeks. The autonomously produced model reaches a held-out score of 0.86 against the top human submission's 0.87 on the public NVIDIA Nemotron-Reasoning Challenge leaderboard, placing 8th of ~4000 at the time of writing. More striking than the number: the loop detected that its own dev metric had stopped tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20657","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/2606.20657/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":"2606.20657","created_at":"2026-06-23T00:11:52.780032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20657v1","created_at":"2026-06-23T00:11:52.780032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20657","created_at":"2026-06-23T00:11:52.780032+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKNZAYC57DXG","created_at":"2026-06-23T00:11:52.780032+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKNZAYC57DXG45E6","created_at":"2026-06-23T00:11:52.780032+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKNZAYC5","created_at":"2026-06-23T00:11:52.780032+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/SKNZAYC57DXG45E6GZC5K5XWPU","json":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU.json","graph_json":"https://pith.science/api/pith-number/SKNZAYC57DXG45E6GZC5K5XWPU/graph.json","events_json":"https://pith.science/api/pith-number/SKNZAYC57DXG45E6GZC5K5XWPU/events.json","paper":"https://pith.science/paper/SKNZAYC5"},"agent_actions":{"view_html":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU","download_json":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU.json","view_paper":"https://pith.science/paper/SKNZAYC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20657&json=true","fetch_graph":"https://pith.science/api/pith-number/SKNZAYC57DXG45E6GZC5K5XWPU/graph.json","fetch_events":"https://pith.science/api/pith-number/SKNZAYC57DXG45E6GZC5K5XWPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU/action/storage_attestation","attest_author":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU/action/author_attestation","sign_citation":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU/action/citation_signature","submit_replication":"https://pith.science/pith/SKNZAYC57DXG45E6GZC5K5XWPU/action/replication_record"}},"created_at":"2026-06-23T00:11:52.780032+00:00","updated_at":"2026-06-23T00:11:52.780032+00:00"}