{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DGZSQ4DLB4AJSNRFCNJJ7K6EQB","short_pith_number":"pith:DGZSQ4DL","schema_version":"1.0","canonical_sha256":"19b328706b0f0099362513529fabc4806619c7a0008a4e326780c4542442868b","source":{"kind":"arxiv","id":"2504.02612","version":2},"attestation_state":"computed","paper":{"title":"Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eunseo Koh, Hyunjun Kim, Jae-Pil Heo, Jiwoo Chung, MinKyu Lee, Sangeek Hyun","submitted_at":"2025-04-03T14:12:55Z","abstract_excerpt":"Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While diffusion-based models produce high-quality images, their extensive denoising steps result in significant computational overhead, limiting real-world applicability. Visual autoregressive (VAR) models, which predict next-scale tokens rather than spatially adjacent ones, offer significantly faster inference suitable for practical deployment. In this paper, we propose th"},"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":"2504.02612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T14:12:55Z","cross_cats_sorted":[],"title_canon_sha256":"a59733700f17d078c92541558dd5efd4a8d667e509a220d35f60281161ed8988","abstract_canon_sha256":"c37662ecaba65af7cfdf2ee99d3d0f7e68a29503f23241436776542d0890528e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:33.429597Z","signature_b64":"EH54QGFARvjn4kXGpiZOU4UQ48t/3OT8A14OMbBSbEm1j5GFCKLBTog7+82jtnhh9mvDDv8q223JlKPE49ZrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19b328706b0f0099362513529fabc4806619c7a0008a4e326780c4542442868b","last_reissued_at":"2026-07-05T11:45:33.429095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:33.429095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eunseo Koh, Hyunjun Kim, Jae-Pil Heo, Jiwoo Chung, MinKyu Lee, Sangeek Hyun","submitted_at":"2025-04-03T14:12:55Z","abstract_excerpt":"Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While diffusion-based models produce high-quality images, their extensive denoising steps result in significant computational overhead, limiting real-world applicability. Visual autoregressive (VAR) models, which predict next-scale tokens rather than spatially adjacent ones, offer significantly faster inference suitable for practical deployment. In this paper, we propose th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02612","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/2504.02612/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":"2504.02612","created_at":"2026-07-05T11:45:33.429154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02612v2","created_at":"2026-07-05T11:45:33.429154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02612","created_at":"2026-07-05T11:45:33.429154+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGZSQ4DLB4AJ","created_at":"2026-07-05T11:45:33.429154+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGZSQ4DLB4AJSNRF","created_at":"2026-07-05T11:45:33.429154+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGZSQ4DL","created_at":"2026-07-05T11:45:33.429154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10407","citing_title":"Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB","json":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB.json","graph_json":"https://pith.science/api/pith-number/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/graph.json","events_json":"https://pith.science/api/pith-number/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/events.json","paper":"https://pith.science/paper/DGZSQ4DL"},"agent_actions":{"view_html":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB","download_json":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB.json","view_paper":"https://pith.science/paper/DGZSQ4DL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02612&json=true","fetch_graph":"https://pith.science/api/pith-number/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/graph.json","fetch_events":"https://pith.science/api/pith-number/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/action/storage_attestation","attest_author":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/action/author_attestation","sign_citation":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/action/citation_signature","submit_replication":"https://pith.science/pith/DGZSQ4DLB4AJSNRFCNJJ7K6EQB/action/replication_record"}},"created_at":"2026-07-05T11:45:33.429154+00:00","updated_at":"2026-07-05T11:45:33.429154+00:00"}