{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C5CXNYZRSOAIEVJIKQ6TVKOR7C","short_pith_number":"pith:C5CXNYZR","schema_version":"1.0","canonical_sha256":"174576e3319380825528543d3aa9d1f89c1410b80ff6a2daaa45381080017944","source":{"kind":"arxiv","id":"2606.05661","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","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","submitted_at":"2026-06-04T03:43:28Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.05661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T03:43:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"746c13a1cbb833fe407e6932f9c59e8e68fa6402a512ca7d64ee55a1a60713f6","abstract_canon_sha256":"2b5a58e0d439548dc4f99b399493d5f042b2fd06ea0996760804cb3f83bdd1e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:58.509847Z","signature_b64":"IMeYYmCBhDNjE5yJ4QYVqgE5sJp+2IPaLmAB3HgxZnFL8dTa82YJy6higwVVrxSToIXldGhR8OENj8BKj3oCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"174576e3319380825528543d3aa9d1f89c1410b80ff6a2daaa45381080017944","last_reissued_at":"2026-06-05T01:14:58.509386Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:58.509386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","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","submitted_at":"2026-06-04T03:43:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05661","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05661/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.05661","created_at":"2026-06-05T01:14:58.509457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05661v1","created_at":"2026-06-05T01:14:58.509457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05661","created_at":"2026-06-05T01:14:58.509457+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5CXNYZRSOAI","created_at":"2026-06-05T01:14:58.509457+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5CXNYZRSOAIEVJI","created_at":"2026-06-05T01:14:58.509457+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5CXNYZR","created_at":"2026-06-05T01:14:58.509457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C","json":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C.json","graph_json":"https://pith.science/api/pith-number/C5CXNYZRSOAIEVJIKQ6TVKOR7C/graph.json","events_json":"https://pith.science/api/pith-number/C5CXNYZRSOAIEVJIKQ6TVKOR7C/events.json","paper":"https://pith.science/paper/C5CXNYZR"},"agent_actions":{"view_html":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C","download_json":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C.json","view_paper":"https://pith.science/paper/C5CXNYZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05661&json=true","fetch_graph":"https://pith.science/api/pith-number/C5CXNYZRSOAIEVJIKQ6TVKOR7C/graph.json","fetch_events":"https://pith.science/api/pith-number/C5CXNYZRSOAIEVJIKQ6TVKOR7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C/action/storage_attestation","attest_author":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C/action/author_attestation","sign_citation":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C/action/citation_signature","submit_replication":"https://pith.science/pith/C5CXNYZRSOAIEVJIKQ6TVKOR7C/action/replication_record"}},"created_at":"2026-06-05T01:14:58.509457+00:00","updated_at":"2026-06-05T01:14:58.509457+00:00"}