{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AL4VNQDFMZJLYCVL2S6WZXJACQ","short_pith_number":"pith:AL4VNQDF","schema_version":"1.0","canonical_sha256":"02f956c0656652bc0aabd4bd6cdd20140fa30e2fbef926f99f8d348b4e2e6e22","source":{"kind":"arxiv","id":"2505.23744","version":1},"attestation_state":"computed","paper":{"title":"Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenhao Ding, Jizhou Han, Qiang Wang, Xiang Song, Xinyuan Gao, Yihong Gong, Yuhang He","submitted_at":"2025-05-29T17:58:57Z","abstract_excerpt":"Deep neural networks (DNNs) often underperform in real-world, dynamic settings where data distributions change over time. Domain Incremental Learning (DIL) offers a solution by enabling continual model adaptation, with Parameter-Isolation DIL (PIDIL) emerging as a promising paradigm to reduce knowledge conflicts. However, existing PIDIL methods struggle with parameter selection accuracy, especially as the number of domains and corresponding classes grows. To address this, we propose SOYO, a lightweight framework that improves domain selection in PIDIL. SOYO introduces a Gaussian Mixture Compre"},"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":"2505.23744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:58:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3542491aa65d6dc8607a50a2ef1f7cab5380e5962bf2a09fe4fb90fd9a052921","abstract_canon_sha256":"7d442b5e189d925a13dfa31d3ae9089bbb3ca6a586eaece99fcd503a50241477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:13.561553Z","signature_b64":"XBKolY7CSIB44T4X86KDYfpc5VyK/PXSLQYFvs1xa1hLI6SX0hRjqpzZG8jFcxXfMGXkEcJ8FaVwogzJes03BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02f956c0656652bc0aabd4bd6cdd20140fa30e2fbef926f99f8d348b4e2e6e22","last_reissued_at":"2026-07-05T11:12:13.561087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:13.561087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenhao Ding, Jizhou Han, Qiang Wang, Xiang Song, Xinyuan Gao, Yihong Gong, Yuhang He","submitted_at":"2025-05-29T17:58:57Z","abstract_excerpt":"Deep neural networks (DNNs) often underperform in real-world, dynamic settings where data distributions change over time. Domain Incremental Learning (DIL) offers a solution by enabling continual model adaptation, with Parameter-Isolation DIL (PIDIL) emerging as a promising paradigm to reduce knowledge conflicts. However, existing PIDIL methods struggle with parameter selection accuracy, especially as the number of domains and corresponding classes grows. To address this, we propose SOYO, a lightweight framework that improves domain selection in PIDIL. SOYO introduces a Gaussian Mixture Compre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23744","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/2505.23744/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":"2505.23744","created_at":"2026-07-05T11:12:13.561141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23744v1","created_at":"2026-07-05T11:12:13.561141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23744","created_at":"2026-07-05T11:12:13.561141+00:00"},{"alias_kind":"pith_short_12","alias_value":"AL4VNQDFMZJL","created_at":"2026-07-05T11:12:13.561141+00:00"},{"alias_kind":"pith_short_16","alias_value":"AL4VNQDFMZJLYCVL","created_at":"2026-07-05T11:12:13.561141+00:00"},{"alias_kind":"pith_short_8","alias_value":"AL4VNQDF","created_at":"2026-07-05T11:12:13.561141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30190","citing_title":"Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ","json":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ.json","graph_json":"https://pith.science/api/pith-number/AL4VNQDFMZJLYCVL2S6WZXJACQ/graph.json","events_json":"https://pith.science/api/pith-number/AL4VNQDFMZJLYCVL2S6WZXJACQ/events.json","paper":"https://pith.science/paper/AL4VNQDF"},"agent_actions":{"view_html":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ","download_json":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ.json","view_paper":"https://pith.science/paper/AL4VNQDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23744&json=true","fetch_graph":"https://pith.science/api/pith-number/AL4VNQDFMZJLYCVL2S6WZXJACQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AL4VNQDFMZJLYCVL2S6WZXJACQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ/action/storage_attestation","attest_author":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ/action/author_attestation","sign_citation":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ/action/citation_signature","submit_replication":"https://pith.science/pith/AL4VNQDFMZJLYCVL2S6WZXJACQ/action/replication_record"}},"created_at":"2026-07-05T11:12:13.561141+00:00","updated_at":"2026-07-05T11:12:13.561141+00:00"}