{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C5CXNYZRSOAIEVJIKQ6TVKOR7C","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":"2b5a58e0d439548dc4f99b399493d5f042b2fd06ea0996760804cb3f83bdd1e5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T03:43:28Z","title_canon_sha256":"746c13a1cbb833fe407e6932f9c59e8e68fa6402a512ca7d64ee55a1a60713f6"},"schema_version":"1.0","source":{"id":"2606.05661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05661","created_at":"2026-06-05T01:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05661v1","created_at":"2026-06-05T01:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05661","created_at":"2026-06-05T01:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"C5CXNYZRSOAI","created_at":"2026-06-05T01:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"C5CXNYZRSOAIEVJI","created_at":"2026-06-05T01:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"C5CXNYZR","created_at":"2026-06-05T01:14:58Z"}],"graph_snapshots":[{"event_id":"sha256:543b12ad5210906def552578ec433400c98b1bdb3229ef783ff83a0aff7528aa","target":"graph","created_at":"2026-06-05T01:14:58Z","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/2606.05661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We introduce Continual Learning Bench (CL-Bench), the first difficult, expert-validated benchmark designed to measure whether LLM-based systems genuinely improve with experience. CL-Bench spans six diverse domains (software engineering, signal processing, disease outbreak forecasting, database querying, strategic game-playing, and demand forecasting), each validated by domain experts and designed so that tasks share a l","authors_text":"Asim Biswal, Benji Xu, Christopher M. Glaze, Frederic Sala, Gabriel Orlanski, Joseph E. Gonzalez, Matei Zaharia, Parth Asawa, Ramya Ramakrishnan, Vincent Sunn Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T03:43:28Z","title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05661","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:a5191c0d078249cf280c17d667ada3fa2ed6cda0981f428ba3388656e9fa09bf","target":"record","created_at":"2026-06-05T01:14:58Z","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":"2b5a58e0d439548dc4f99b399493d5f042b2fd06ea0996760804cb3f83bdd1e5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T03:43:28Z","title_canon_sha256":"746c13a1cbb833fe407e6932f9c59e8e68fa6402a512ca7d64ee55a1a60713f6"},"schema_version":"1.0","source":{"id":"2606.05661","kind":"arxiv","version":1}},"canonical_sha256":"174576e3319380825528543d3aa9d1f89c1410b80ff6a2daaa45381080017944","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"174576e3319380825528543d3aa9d1f89c1410b80ff6a2daaa45381080017944","first_computed_at":"2026-06-05T01:14:58.509386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:58.509386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IMeYYmCBhDNjE5yJ4QYVqgE5sJp+2IPaLmAB3HgxZnFL8dTa82YJy6higwVVrxSToIXldGhR8OENj8BKj3oCAQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:58.509847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5191c0d078249cf280c17d667ada3fa2ed6cda0981f428ba3388656e9fa09bf","sha256:543b12ad5210906def552578ec433400c98b1bdb3229ef783ff83a0aff7528aa"],"state_sha256":"837c15279b1b7e0c63529add6abfd3eebd4f213874ae2463bb1d262247bea4b7"}