{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJ6VGYMB3GHXAUCJ6QYGT4VQVJ","short_pith_number":"pith:HJ6VGYMB","schema_version":"1.0","canonical_sha256":"3a7d536181d98f705049f43069f2b0aa684c651ce5d5fe4580e212769cddd1a1","source":{"kind":"arxiv","id":"2605.28444","version":1},"attestation_state":"computed","paper":{"title":"Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinwook Jung, Jungyong Son, Minhee Park, Sungyong Baik","submitted_at":"2026-05-27T13:10:34Z","abstract_excerpt":"Fine-tuning large-scale pre-trained models is a recent prevalent paradigm for adapting general representations to specialized tasks. However, when a new version of a pre-trained model becomes available, expertise acquired through fine-tuning cannot be directly reused because it is tied to the parameterization of the original model, requiring another costly fine-tuning. To address this inefficiency, recent work uses task vectors, defined as the parameter difference between a fine-tuned model and its base model, to transfer expertise across models. While existing methods bridge disparate models "},"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":"2605.28444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T13:10:34Z","cross_cats_sorted":[],"title_canon_sha256":"f386738b879587621f765bcef36eb1ee14c2792783925c932f6f75e9ab163957","abstract_canon_sha256":"f2adb6466f97a6504fa7a51b9bbbe8fc6b5c4121062d98faf6e5b662f7d3fdf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:53.237205Z","signature_b64":"/lONQ6rg5Cih1lgS/kPe4et8FqOclqjQZ9QvQzD9pCifynSnwuhIZUAzzwyDquOXRC+xauSjAgQtO1tPrbGhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a7d536181d98f705049f43069f2b0aa684c651ce5d5fe4580e212769cddd1a1","last_reissued_at":"2026-05-28T02:04:53.236771Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:53.236771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinwook Jung, Jungyong Son, Minhee Park, Sungyong Baik","submitted_at":"2026-05-27T13:10:34Z","abstract_excerpt":"Fine-tuning large-scale pre-trained models is a recent prevalent paradigm for adapting general representations to specialized tasks. However, when a new version of a pre-trained model becomes available, expertise acquired through fine-tuning cannot be directly reused because it is tied to the parameterization of the original model, requiring another costly fine-tuning. To address this inefficiency, recent work uses task vectors, defined as the parameter difference between a fine-tuned model and its base model, to transfer expertise across models. While existing methods bridge disparate models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28444","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/2605.28444/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":"2605.28444","created_at":"2026-05-28T02:04:53.236826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28444v1","created_at":"2026-05-28T02:04:53.236826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28444","created_at":"2026-05-28T02:04:53.236826+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJ6VGYMB3GHX","created_at":"2026-05-28T02:04:53.236826+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJ6VGYMB3GHXAUCJ","created_at":"2026-05-28T02:04:53.236826+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJ6VGYMB","created_at":"2026-05-28T02:04:53.236826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ","json":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ.json","graph_json":"https://pith.science/api/pith-number/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/graph.json","events_json":"https://pith.science/api/pith-number/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/events.json","paper":"https://pith.science/paper/HJ6VGYMB"},"agent_actions":{"view_html":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ","download_json":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ.json","view_paper":"https://pith.science/paper/HJ6VGYMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28444&json=true","fetch_graph":"https://pith.science/api/pith-number/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/action/storage_attestation","attest_author":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/action/author_attestation","sign_citation":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/action/citation_signature","submit_replication":"https://pith.science/pith/HJ6VGYMB3GHXAUCJ6QYGT4VQVJ/action/replication_record"}},"created_at":"2026-05-28T02:04:53.236826+00:00","updated_at":"2026-05-28T02:04:53.236826+00:00"}