{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CA7G57KQJ3KZCRQKMC2IKDPJ4Z","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":"f95b0bf059b78ecc1b2e59d9e6aa38d0a00d7cc9ff6a8b73f978a2984182829f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:35:20Z","title_canon_sha256":"cf92ca72477970bb06061a179b8bd8805b85e946faf1143b3d1fd2be39f9a34b"},"schema_version":"1.0","source":{"id":"2502.15224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15224","created_at":"2026-06-01T01:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15224v2","created_at":"2026-06-01T01:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15224","created_at":"2026-06-01T01:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"CA7G57KQJ3KZ","created_at":"2026-06-01T01:03:39Z"},{"alias_kind":"pith_short_16","alias_value":"CA7G57KQJ3KZCRQK","created_at":"2026-06-01T01:03:39Z"},{"alias_kind":"pith_short_8","alias_value":"CA7G57KQ","created_at":"2026-06-01T01:03:39Z"}],"graph_snapshots":[{"event_id":"sha256:d014f712911c868bdcc92e7d11e8cc920f1b7fa03a0774ab5273a43760b61b11","target":"graph","created_at":"2026-06-01T01:03:39Z","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/2502.15224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interactive discovery requires agents to maintain and update structured beliefs over many rounds of feedback. Before evaluating agents in noisy, open-ended scientific environments, it is useful to isolate this prerequisite capability under controlled conditions. We introduce Auto-Discovery-Bench, a deterministic oracle-guided diagnostic benchmark in which agents recover hidden structures through repeated hypothesis--intervention--feedback cycles. The benchmark instantiates three controlled discovery abstractions: directed graph discovery, undirected relational discovery, and symbolic equation ","authors_text":"Anirudh Goyal, Beibei Lin, Dianbo Liu, Qiran Zou, Srinivas Anumasa, Tingting Chen, Vedant Shah, Zifeng Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:35:20Z","title":"Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15224","kind":"arxiv","version":2},"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":"sha256:70718c96639e0bad64aa56cfe8131218e2539caf58a40d3a22e0e5f3eac88a65","target":"record","created_at":"2026-06-01T01:03:39Z","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":"f95b0bf059b78ecc1b2e59d9e6aa38d0a00d7cc9ff6a8b73f978a2984182829f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-21T05:35:20Z","title_canon_sha256":"cf92ca72477970bb06061a179b8bd8805b85e946faf1143b3d1fd2be39f9a34b"},"schema_version":"1.0","source":{"id":"2502.15224","kind":"arxiv","version":2}},"canonical_sha256":"103e6efd504ed591460a60b4850de9e67fccb5e8d543950c032a020d50a24213","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"103e6efd504ed591460a60b4850de9e67fccb5e8d543950c032a020d50a24213","first_computed_at":"2026-06-01T01:03:39.694676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:39.694676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tj6kkuSZSunY5sWDRXQSOn2/8vVyfUAkEauqBozi1fhu03Pq/IWuhlMe2d657sBDgqSGjz+NRqfopUlqvSviDQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:39.695399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70718c96639e0bad64aa56cfe8131218e2539caf58a40d3a22e0e5f3eac88a65","sha256:d014f712911c868bdcc92e7d11e8cc920f1b7fa03a0774ab5273a43760b61b11"],"state_sha256":"d2d5faf299a3d8e1a65794e24505fd7b3c99f66a1fa72c4537f84d7d729a054c"}