{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HUCA6C6TPJHKU2LURUP6FDZFSY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2c1a4bf7f2c42ddf761b87fe31965f5a7b48b5ec960aaad75e8e611bab997c9c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T16:08:31Z","title_canon_sha256":"456c1a9eb2b9676f40db5d340714d12f1060266947e7b716d5fbd322cefa09a1"},"schema_version":"1.0","source":{"id":"2606.25996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25996","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25996v1","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25996","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"HUCA6C6TPJHK","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"HUCA6C6TPJHKU2LU","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"HUCA6C6T","created_at":"2026-06-25T01:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:e31eb93f6cb4c7f40d030e5d400b31dad1c38a4648a9f381fd7c71f2c05e9ec8","target":"graph","created_at":"2026-06-25T01:18:45Z","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/2606.25996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how to train (meta-optimize) such a data scientist agent, so that it learns to create even stronger data. We describe the overall formulation, and a specific practical implementation, Agentic Self-Instruct. We conduct experiments on computer science research tasks, legal reasoning tasks and reasoning with mathematical objects, where we obtain improved results compared to classical synthetic dataset creation methods. Further, meta-optimizing the d","authors_text":"Chenxi Whitehouse, Eryk Helenowski, Han Fang, Ilia Kulikov, Jack Lanchantin, Jakob Foerster, Jason Weston, Olga Golovneva, Sainbayar Sukhbaatar, Swarnadeep Saha, Tianhao Wu, Weizhe Yuan, Xian Li, Yixin Nie, Yoram Bachrach","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T16:08:31Z","title":"Autodata: An agentic data scientist to create high quality synthetic data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25996","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:d548fb7bb56e6f0ded7e765c0a55b80f21f4bfe2b1f49ecada0c6b5cbc17b782","target":"record","created_at":"2026-06-25T01:18:45Z","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":"2c1a4bf7f2c42ddf761b87fe31965f5a7b48b5ec960aaad75e8e611bab997c9c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T16:08:31Z","title_canon_sha256":"456c1a9eb2b9676f40db5d340714d12f1060266947e7b716d5fbd322cefa09a1"},"schema_version":"1.0","source":{"id":"2606.25996","kind":"arxiv","version":1}},"canonical_sha256":"3d040f0bd37a4eaa69748d1fe28f25963dd4cf99b38111ec748a370c265d0abc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d040f0bd37a4eaa69748d1fe28f25963dd4cf99b38111ec748a370c265d0abc","first_computed_at":"2026-06-25T01:18:45.314404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:45.314404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jb5sg7oTSIVpjyk/wvQW8LiNlvVpymEw5JyUN5F7rfZPNKBEGIkaRfx4SjiolE4MeUz8SPrqEWuqolZEwTBaDQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:45.314759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d548fb7bb56e6f0ded7e765c0a55b80f21f4bfe2b1f49ecada0c6b5cbc17b782","sha256:e31eb93f6cb4c7f40d030e5d400b31dad1c38a4648a9f381fd7c71f2c05e9ec8"],"state_sha256":"90efebfdce790b6f67f61e6f66e5a51f9a43254ae57466e5b9b589dbae74931d"}