{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SH25GJLM4ZVTRFMTOJENWKADXD","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":"b6271d9783f25835fed65781142fb08768d40036e1376b2ccc3998b7c3400652","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T16:12:55Z","title_canon_sha256":"9e77f32abd30c68fa4254f0d8b34a1a14dcc944a56598d317fcdf3cd5c93b4e7"},"schema_version":"1.0","source":{"id":"2606.11045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11045","created_at":"2026-06-10T01:11:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11045v1","created_at":"2026-06-10T01:11:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11045","created_at":"2026-06-10T01:11:06Z"},{"alias_kind":"pith_short_12","alias_value":"SH25GJLM4ZVT","created_at":"2026-06-10T01:11:06Z"},{"alias_kind":"pith_short_16","alias_value":"SH25GJLM4ZVTRFMT","created_at":"2026-06-10T01:11:06Z"},{"alias_kind":"pith_short_8","alias_value":"SH25GJLM","created_at":"2026-06-10T01:11:06Z"}],"graph_snapshots":[{"event_id":"sha256:f790d7a76e353e21ec86238a1a5060c3f0bdd73324d41687e2942511c539e51d","target":"graph","created_at":"2026-06-10T01:11:06Z","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/2606.11045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practice. An attractive hypothesis is that successful ML strategies are highly compressible. We study this in the setting of LLM-driven research agents, where the hypothesis becomes directly testable via two complementary information bottlenecks. In \\emph{output compression}, an exploration agent adaptively searches for high-performance models using a validation set, and we test whether a fresh ``reproducer agent'' can repr","authors_text":"Aaron Roth, Martin Andres Bertran, Zhiwei Steven Wu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T16:12:55Z","title":"What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11045","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:d5aa7dbd2a7329c7f560fdc0f4a44fc7dc6f2a54ac246b67f21735e55f0014e6","target":"record","created_at":"2026-06-10T01:11:06Z","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":"b6271d9783f25835fed65781142fb08768d40036e1376b2ccc3998b7c3400652","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T16:12:55Z","title_canon_sha256":"9e77f32abd30c68fa4254f0d8b34a1a14dcc944a56598d317fcdf3cd5c93b4e7"},"schema_version":"1.0","source":{"id":"2606.11045","kind":"arxiv","version":1}},"canonical_sha256":"91f5d3256ce66b3895937248db2803b8d91a0c11d59240d5aec47639a26f1946","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91f5d3256ce66b3895937248db2803b8d91a0c11d59240d5aec47639a26f1946","first_computed_at":"2026-06-10T01:11:06.658905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:11:06.658905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wPt1zaVkGFl5zSCOQDfrhgI3A+cTpaMywtgFrgmK2vl8fAgT6+DT1D8MaTK5kOIzT8WXo8PqFj20gezkTjcPAQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:11:06.659768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5aa7dbd2a7329c7f560fdc0f4a44fc7dc6f2a54ac246b67f21735e55f0014e6","sha256:f790d7a76e353e21ec86238a1a5060c3f0bdd73324d41687e2942511c539e51d"],"state_sha256":"5742efac1418c669f5ff11e2cd3963f5bc98904961e739432687101a381c2e44"}