{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EKFEF5VVR6Z5CNS7AA5F4KESI","short_pith_number":"pith:6EKFEF5V","schema_version":"1.0","canonical_sha256":"f1145217b5ac7d9e89b2f801d2f144921dcbf6f712066f81e87fb414cfe6fd24","source":{"kind":"arxiv","id":"2405.14124","version":4},"attestation_state":"computed","paper":{"title":"Mixture of Experts Meets Prompt-Based Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An Nguyen, Huy Nguyen, Linh Van Ngo, Minh Le, Nhat Ho, Trang Nguyen, Trang Pham","submitted_at":"2024-05-23T02:49:57Z","abstract_excerpt":"Exploiting the power of pre-trained models, prompt-based approaches stand out compared to other continual learning solutions in effectively preventing catastrophic forgetting, even with very few learnable parameters and without the need for a memory buffer. While existing prompt-based continual learning methods excel in leveraging prompts for state-of-the-art performance, they often lack a theoretical explanation for the effectiveness of prompting. This paper conducts a theoretical analysis to unravel how prompts bestow such advantages in continual learning, thus offering a new perspective on "},"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":"2405.14124","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T02:49:57Z","cross_cats_sorted":[],"title_canon_sha256":"1ec24974e2f9197393e92bfb5296a4c97d79e1da4d607f2f439bc613631052fb","abstract_canon_sha256":"606fe3f250327eed15b3229b484df8255bd31ccdaadd53dbede6653cfb9f2a73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:51.639614Z","signature_b64":"cM1M+IZuO901H4q2YS2iRlAq/gMhxGpSHcGrUZxuVejvWQgPlJTwfHJe1mAvKZfqTLsd6DV7ufPQ2Y51+8LJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1145217b5ac7d9e89b2f801d2f144921dcbf6f712066f81e87fb414cfe6fd24","last_reissued_at":"2026-07-05T09:56:51.639115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:51.639115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture of Experts Meets Prompt-Based Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An Nguyen, Huy Nguyen, Linh Van Ngo, Minh Le, Nhat Ho, Trang Nguyen, Trang Pham","submitted_at":"2024-05-23T02:49:57Z","abstract_excerpt":"Exploiting the power of pre-trained models, prompt-based approaches stand out compared to other continual learning solutions in effectively preventing catastrophic forgetting, even with very few learnable parameters and without the need for a memory buffer. While existing prompt-based continual learning methods excel in leveraging prompts for state-of-the-art performance, they often lack a theoretical explanation for the effectiveness of prompting. This paper conducts a theoretical analysis to unravel how prompts bestow such advantages in continual learning, thus offering a new perspective on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14124","kind":"arxiv","version":4},"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/2405.14124/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":"2405.14124","created_at":"2026-07-05T09:56:51.639186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14124v4","created_at":"2026-07-05T09:56:51.639186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14124","created_at":"2026-07-05T09:56:51.639186+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EKFEF5VVR6Z","created_at":"2026-07-05T09:56:51.639186+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EKFEF5VVR6Z5CNS","created_at":"2026-07-05T09:56:51.639186+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EKFEF5V","created_at":"2026-07-05T09:56:51.639186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16930","citing_title":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI","json":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI.json","graph_json":"https://pith.science/api/pith-number/6EKFEF5VVR6Z5CNS7AA5F4KESI/graph.json","events_json":"https://pith.science/api/pith-number/6EKFEF5VVR6Z5CNS7AA5F4KESI/events.json","paper":"https://pith.science/paper/6EKFEF5V"},"agent_actions":{"view_html":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI","download_json":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI.json","view_paper":"https://pith.science/paper/6EKFEF5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14124&json=true","fetch_graph":"https://pith.science/api/pith-number/6EKFEF5VVR6Z5CNS7AA5F4KESI/graph.json","fetch_events":"https://pith.science/api/pith-number/6EKFEF5VVR6Z5CNS7AA5F4KESI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI/action/storage_attestation","attest_author":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI/action/author_attestation","sign_citation":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI/action/citation_signature","submit_replication":"https://pith.science/pith/6EKFEF5VVR6Z5CNS7AA5F4KESI/action/replication_record"}},"created_at":"2026-07-05T09:56:51.639186+00:00","updated_at":"2026-07-05T09:56:51.639186+00:00"}