{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MMUZEXYLMKPEXX3655UHPTYM5C","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":"bf76767bb4402e756114ab2ac074c0692659424124243a64102f6336d2557f31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T16:53:45Z","title_canon_sha256":"6910500003e7fb7262fe42b048242c5231358424e5dace89d816d637d513eba5"},"schema_version":"1.0","source":{"id":"2502.03358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03358","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03358v2","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03358","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"MMUZEXYLMKPE","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"MMUZEXYLMKPEXX36","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"MMUZEXYL","created_at":"2026-07-05T11:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:764e1bfd30c26b9de1b53e0dd618e419067b7395fb57650ad18368b55990858c","target":"graph","created_at":"2026-07-05T11:18:17Z","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/2502.03358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How effectively can LLM-based AI assistants utilize their memory (context) to perform various tasks? Traditional data benchmarks, which are often manually crafted, suffer from several limitations: they are static, susceptible to overfitting, difficult to interpret, and lack actionable insights--failing to pinpoint the specific capabilities a model lacks when it does not pass a test. In this paper, we present a framework for automatically generating a comprehensive set of tests to evaluate models' abilities to use their memory effectively. Our framework extends the range of capability tests bey","authors_text":"Menglin Xia, Reza Shokri, Saravan Rajmohan, Victor Ruehle","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T16:53:45Z","title":"Minerva: A Programmable Memory Test Benchmark for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03358","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:d7f2ecbda4ff96cf30c2d2ca9309064f8e1c844cf0167e0ac92b067365dad69e","target":"record","created_at":"2026-07-05T11:18:17Z","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":"bf76767bb4402e756114ab2ac074c0692659424124243a64102f6336d2557f31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-05T16:53:45Z","title_canon_sha256":"6910500003e7fb7262fe42b048242c5231358424e5dace89d816d637d513eba5"},"schema_version":"1.0","source":{"id":"2502.03358","kind":"arxiv","version":2}},"canonical_sha256":"6329925f0b629e4bdf7eef6877cf0ce89ac1daa949f18b3d34f60eca81efbaff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6329925f0b629e4bdf7eef6877cf0ce89ac1daa949f18b3d34f60eca81efbaff","first_computed_at":"2026-07-05T11:18:17.548676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:17.548676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N3lv1sw2gRIwXEk6gsKC0vNy6al9qzrFOUITv5x87v1Gw9j2uiOMXgVDuT5zGvzGOj9u6AtrePjYggpvFfn7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:17.549188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7f2ecbda4ff96cf30c2d2ca9309064f8e1c844cf0167e0ac92b067365dad69e","sha256:764e1bfd30c26b9de1b53e0dd618e419067b7395fb57650ad18368b55990858c"],"state_sha256":"d3b15fdefa98674e401ac65c84833a3cee8491fd651bf90791f23549383d7bad"}