{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFR3QHMNFJ3KOI2MTJ4MTXCCSO","short_pith_number":"pith:RFR3QHMN","schema_version":"1.0","canonical_sha256":"8963b81d8d2a76a7234c9a78c9dc4293bf7df129cb73fef4be52edea65c5517b","source":{"kind":"arxiv","id":"2410.02147","version":2},"attestation_state":"computed","paper":{"title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Ali Moin, Behrooz Mahasseni, Christopher Sandino, Ellen L Zippi, Erdrin Azemi, Gaurav Patel, Juri Minxha","submitted_at":"2024-10-03T02:12:03Z","abstract_excerpt":"In this paper, we propose a framework for efficient Source-Free Domain Adaptation (SFDA) in the context of time-series, focusing on enhancing both parameter efficiency and data-sample utilization. Our approach introduces an improved paradigm for source-model preparation and target-side adaptation, aiming to enhance training efficiency during target adaptation. Specifically, we reparameterize the source model's weights in a Tucker-style decomposed manner, factorizing the model into a compact form during the source model preparation phase. During target-side adaptation, only a subset of these de"},"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":"2410.02147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T02:12:03Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"ce8ba1726031b3dfc6ebee8fa56c53da55b5c985aaa981612978b28b4e7c2492","abstract_canon_sha256":"6612e0534038c022f9ade0fb5e0ecde1a922bb721c1eae4ecb590d19f8cd8ff9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:22.174931Z","signature_b64":"ftmW43vLQUNwgd4jTDIpYcbUrKWVd+gKvxKltRhmGQ9reD6pP9sc5WM91I89uM34LoeSl5Q3xNovaJ6VZ2o6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8963b81d8d2a76a7234c9a78c9dc4293bf7df129cb73fef4be52edea65c5517b","last_reissued_at":"2026-07-05T10:08:22.174498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:22.174498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Ali Moin, Behrooz Mahasseni, Christopher Sandino, Ellen L Zippi, Erdrin Azemi, Gaurav Patel, Juri Minxha","submitted_at":"2024-10-03T02:12:03Z","abstract_excerpt":"In this paper, we propose a framework for efficient Source-Free Domain Adaptation (SFDA) in the context of time-series, focusing on enhancing both parameter efficiency and data-sample utilization. Our approach introduces an improved paradigm for source-model preparation and target-side adaptation, aiming to enhance training efficiency during target adaptation. Specifically, we reparameterize the source model's weights in a Tucker-style decomposed manner, factorizing the model into a compact form during the source model preparation phase. During target-side adaptation, only a subset of these de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02147","kind":"arxiv","version":2},"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/2410.02147/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":"2410.02147","created_at":"2026-07-05T10:08:22.174554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02147v2","created_at":"2026-07-05T10:08:22.174554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02147","created_at":"2026-07-05T10:08:22.174554+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFR3QHMNFJ3K","created_at":"2026-07-05T10:08:22.174554+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFR3QHMNFJ3KOI2M","created_at":"2026-07-05T10:08:22.174554+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFR3QHMN","created_at":"2026-07-05T10:08:22.174554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10855","citing_title":"Sparse Fine-Tuning of Transformers for Generative Tasks","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO","json":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO.json","graph_json":"https://pith.science/api/pith-number/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/graph.json","events_json":"https://pith.science/api/pith-number/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/events.json","paper":"https://pith.science/paper/RFR3QHMN"},"agent_actions":{"view_html":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO","download_json":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO.json","view_paper":"https://pith.science/paper/RFR3QHMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02147&json=true","fetch_graph":"https://pith.science/api/pith-number/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/graph.json","fetch_events":"https://pith.science/api/pith-number/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/action/storage_attestation","attest_author":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/action/author_attestation","sign_citation":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/action/citation_signature","submit_replication":"https://pith.science/pith/RFR3QHMNFJ3KOI2MTJ4MTXCCSO/action/replication_record"}},"created_at":"2026-07-05T10:08:22.174554+00:00","updated_at":"2026-07-05T10:08:22.174554+00:00"}