{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HBAKSWXAH4AM3JRTBMKAWYHQ6Q","short_pith_number":"pith:HBAKSWXA","schema_version":"1.0","canonical_sha256":"3840a95ae03f00cda6330b140b60f0f41fd6e30706116b59c2c9d7a42bb09262","source":{"kind":"arxiv","id":"2502.06544","version":1},"attestation_state":"computed","paper":{"title":"Sequence Transferability and Task Order Selection in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Binh T. Nguyen, Cuong N. Nguyen, Cuong V. Nguyen, Quang Pham, Savitha Ramasamy, Thinh Nguyen, Xiaoli Li","submitted_at":"2025-02-10T15:09:56Z","abstract_excerpt":"In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accuracy. However, efforts in this direction remain underdeveloped despite encouraging progress in methodology development. In this work, we investigate the impacts of sequence transferability on continual learning and propose two novel measures that capture the total transferability of a task sequence, either in the forward or backward direction. Based on the empirical properties of these measures, we then develop a new "},"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":"2502.06544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T15:09:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f9a13cb619dc2a879dbbaa6589ffb7062eff6b9acd3df1d520dac327bb6ece1a","abstract_canon_sha256":"ebb7a924206844368f94c334217d3108c19bdd1d8b1550b4be2578282c3ad5d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:08.288771Z","signature_b64":"tpBPCOsQj2ybe8DjkhkYiFE/api5WMpkTXlJ/MPjH9j17SRcTg060bcvyRjuVSG+x2HPv/qhVzObW6PMQ6XvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3840a95ae03f00cda6330b140b60f0f41fd6e30706116b59c2c9d7a42bb09262","last_reissued_at":"2026-07-05T10:12:08.288251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:08.288251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence Transferability and Task Order Selection in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Binh T. Nguyen, Cuong N. Nguyen, Cuong V. Nguyen, Quang Pham, Savitha Ramasamy, Thinh Nguyen, Xiaoli Li","submitted_at":"2025-02-10T15:09:56Z","abstract_excerpt":"In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accuracy. However, efforts in this direction remain underdeveloped despite encouraging progress in methodology development. In this work, we investigate the impacts of sequence transferability on continual learning and propose two novel measures that capture the total transferability of a task sequence, either in the forward or backward direction. Based on the empirical properties of these measures, we then develop a new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06544","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/2502.06544/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":"2502.06544","created_at":"2026-07-05T10:12:08.288320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06544v1","created_at":"2026-07-05T10:12:08.288320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06544","created_at":"2026-07-05T10:12:08.288320+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBAKSWXAH4AM","created_at":"2026-07-05T10:12:08.288320+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBAKSWXAH4AM3JRT","created_at":"2026-07-05T10:12:08.288320+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBAKSWXA","created_at":"2026-07-05T10:12:08.288320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24993","citing_title":"The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q","json":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q.json","graph_json":"https://pith.science/api/pith-number/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/graph.json","events_json":"https://pith.science/api/pith-number/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/events.json","paper":"https://pith.science/paper/HBAKSWXA"},"agent_actions":{"view_html":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q","download_json":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q.json","view_paper":"https://pith.science/paper/HBAKSWXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06544&json=true","fetch_graph":"https://pith.science/api/pith-number/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/action/storage_attestation","attest_author":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/action/author_attestation","sign_citation":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/action/citation_signature","submit_replication":"https://pith.science/pith/HBAKSWXAH4AM3JRTBMKAWYHQ6Q/action/replication_record"}},"created_at":"2026-07-05T10:12:08.288320+00:00","updated_at":"2026-07-05T10:12:08.288320+00:00"}