{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VLGJHTZB3YOYHARNQBYXAX2GGA","short_pith_number":"pith:VLGJHTZB","schema_version":"1.0","canonical_sha256":"aacc93cf21de1d83822d8071705f463005ecb40985eb38f83b53999b0ad72618","source":{"kind":"arxiv","id":"2602.15727","version":2},"attestation_state":"computed","paper":{"title":"Spanning the Visual Analogy Space with a Weight Basis of LoRAs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gal Chechik, Haggai Maron, Hila Manor, Rinon Gal, Tomer Michaeli","submitted_at":"2026-02-17T17:02:38Z","abstract_excerpt":"Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\\{\\mathbf{a}$, $\\mathbf{a}'$, $\\mathbf{b}\\}$, the goal is to generate $\\mathbf{b}'$ such that $\\mathbf{a} : \\mathbf{a}' :: \\mathbf{b} : \\mathbf{b}'$. Recent methods adapt text-to-image models with a single Low-Rank Adaptation (LoRA) module, but they face a fundamental limitation: attempting to capture the diverse space of visual transformations within a fixed module constrains generalization. Inspir"},"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":"2602.15727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-17T17:02:38Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG","eess.IV"],"title_canon_sha256":"1b6f270517311a264729e277c649ae6f072446f0f20ca1c0a908eac4a749aad2","abstract_canon_sha256":"4af57d030ca72fdb971a1c7a6efc155edd550f02f42af4f98aa8ae346822104c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:34.189185Z","signature_b64":"Yv/onbL/E0KLtFvzJ10SD59qtqyP3T+euHDGa0X9Bhp1ShGIwPvEDr5T8aEw9BqASCxaepCC5/GL+werqWYIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aacc93cf21de1d83822d8071705f463005ecb40985eb38f83b53999b0ad72618","last_reissued_at":"2026-06-30T01:17:34.188381Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:34.188381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spanning the Visual Analogy Space with a Weight Basis of LoRAs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gal Chechik, Haggai Maron, Hila Manor, Rinon Gal, Tomer Michaeli","submitted_at":"2026-02-17T17:02:38Z","abstract_excerpt":"Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\\{\\mathbf{a}$, $\\mathbf{a}'$, $\\mathbf{b}\\}$, the goal is to generate $\\mathbf{b}'$ such that $\\mathbf{a} : \\mathbf{a}' :: \\mathbf{b} : \\mathbf{b}'$. Recent methods adapt text-to-image models with a single Low-Rank Adaptation (LoRA) module, but they face a fundamental limitation: attempting to capture the diverse space of visual transformations within a fixed module constrains generalization. Inspir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15727","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/2602.15727/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":"2602.15727","created_at":"2026-06-30T01:17:34.188499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.15727v2","created_at":"2026-06-30T01:17:34.188499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15727","created_at":"2026-06-30T01:17:34.188499+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLGJHTZB3YOY","created_at":"2026-06-30T01:17:34.188499+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLGJHTZB3YOYHARN","created_at":"2026-06-30T01:17:34.188499+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLGJHTZB","created_at":"2026-06-30T01:17:34.188499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.07940","citing_title":"Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA","json":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA.json","graph_json":"https://pith.science/api/pith-number/VLGJHTZB3YOYHARNQBYXAX2GGA/graph.json","events_json":"https://pith.science/api/pith-number/VLGJHTZB3YOYHARNQBYXAX2GGA/events.json","paper":"https://pith.science/paper/VLGJHTZB"},"agent_actions":{"view_html":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA","download_json":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA.json","view_paper":"https://pith.science/paper/VLGJHTZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.15727&json=true","fetch_graph":"https://pith.science/api/pith-number/VLGJHTZB3YOYHARNQBYXAX2GGA/graph.json","fetch_events":"https://pith.science/api/pith-number/VLGJHTZB3YOYHARNQBYXAX2GGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA/action/storage_attestation","attest_author":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA/action/author_attestation","sign_citation":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA/action/citation_signature","submit_replication":"https://pith.science/pith/VLGJHTZB3YOYHARNQBYXAX2GGA/action/replication_record"}},"created_at":"2026-06-30T01:17:34.188499+00:00","updated_at":"2026-06-30T01:17:34.188499+00:00"}