{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PZUGXCZSGXKXAP2ZVB776W7EPJ","short_pith_number":"pith:PZUGXCZS","schema_version":"1.0","canonical_sha256":"7e686b8b3235d5703f59a87fff5be47a7e16c3a57d112f206a11d03cd438a337","source":{"kind":"arxiv","id":"2404.00790","version":1},"attestation_state":"computed","paper":{"title":"Rehearsal-Free Modular and Compositional Continual Learning for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Heike Adel, Hinrich Sch\\\"utze, Jannik Str\\\"otgen, Lukas Lange, Mingyang Wang","submitted_at":"2024-03-31T20:28:44Z","abstract_excerpt":"Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal-based, i.e., store data examples from previous tasks for data replay, or isolate parameters dedicated to each task. However, rehearsal-based methods raise privacy and memory issues, and parameter-isolation continual learning does not consider interaction between tasks, thus hindering knowledge transfer. In this work, we propose MoCL, a rehearsal-free Modular and Compositional Continual Learning framework which continually ad"},"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":"2404.00790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-31T20:28:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e77ff1929fffb0aababe678dea2f225950c51a8508f75949052d5f49a0ea8d00","abstract_canon_sha256":"01b438250abadc0a3b133ca56c9f98d1c29e1f7b0fd051b8952b344b4bffc420"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:56.665350Z","signature_b64":"rdKsJdIdYeQj7jvx/uBm3basY7i7kk5ad1UO8BmGcF8t47NE1ApJzcjAuCjzVSAVGoSzxqDuKNh4zC4Sq+/vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e686b8b3235d5703f59a87fff5be47a7e16c3a57d112f206a11d03cd438a337","last_reissued_at":"2026-07-05T08:02:56.664836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:56.664836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rehearsal-Free Modular and Compositional Continual Learning for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Heike Adel, Hinrich Sch\\\"utze, Jannik Str\\\"otgen, Lukas Lange, Mingyang Wang","submitted_at":"2024-03-31T20:28:44Z","abstract_excerpt":"Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal-based, i.e., store data examples from previous tasks for data replay, or isolate parameters dedicated to each task. However, rehearsal-based methods raise privacy and memory issues, and parameter-isolation continual learning does not consider interaction between tasks, thus hindering knowledge transfer. In this work, we propose MoCL, a rehearsal-free Modular and Compositional Continual Learning framework which continually ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00790","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/2404.00790/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":"2404.00790","created_at":"2026-07-05T08:02:56.664895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00790v1","created_at":"2026-07-05T08:02:56.664895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00790","created_at":"2026-07-05T08:02:56.664895+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZUGXCZSGXKX","created_at":"2026-07-05T08:02:56.664895+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZUGXCZSGXKXAP2Z","created_at":"2026-07-05T08:02:56.664895+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZUGXCZS","created_at":"2026-07-05T08:02:56.664895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05808","citing_title":"STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ","json":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ.json","graph_json":"https://pith.science/api/pith-number/PZUGXCZSGXKXAP2ZVB776W7EPJ/graph.json","events_json":"https://pith.science/api/pith-number/PZUGXCZSGXKXAP2ZVB776W7EPJ/events.json","paper":"https://pith.science/paper/PZUGXCZS"},"agent_actions":{"view_html":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ","download_json":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ.json","view_paper":"https://pith.science/paper/PZUGXCZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00790&json=true","fetch_graph":"https://pith.science/api/pith-number/PZUGXCZSGXKXAP2ZVB776W7EPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PZUGXCZSGXKXAP2ZVB776W7EPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ/action/storage_attestation","attest_author":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ/action/author_attestation","sign_citation":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ/action/citation_signature","submit_replication":"https://pith.science/pith/PZUGXCZSGXKXAP2ZVB776W7EPJ/action/replication_record"}},"created_at":"2026-07-05T08:02:56.664895+00:00","updated_at":"2026-07-05T08:02:56.664895+00:00"}