{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IRDBZJGHW6WFJ776XFG44CJDU5","short_pith_number":"pith:IRDBZJGH","schema_version":"1.0","canonical_sha256":"44461ca4c7b7ac54fffeb94dce0923a768ed4b3cd27df6d2f480ec6ec4f721c5","source":{"kind":"arxiv","id":"2412.16334","version":1},"attestation_state":"computed","paper":{"title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cijo Jose, Dahyun Kang, Daniel Li, Federico Baldassarre, Hu Xu, Huy V. Vo, Marc Szafraniec, Maxime Oquab, Micha\\\"el Ramamonjisoa, Oriane Sim\\'eoni, Patrick Labatut, Piotr Bojanowski, Th\\'eo Moutakanni, Timoth\\'ee Darcet","submitted_at":"2024-12-20T20:46:48Z","abstract_excerpt":"Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not readily aligned with language, hindering their adoption in open-vocabulary tasks. Our method, named dino.txt, unlocks this new ability for DINOv2, a widely used self-supervised visual encoder. We build upon the LiT training strategy, which trains a text encoder to align with a frozen vision model but leads to unsatisfactory results on dense tasks. We propose seve"},"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":"2412.16334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T20:46:48Z","cross_cats_sorted":[],"title_canon_sha256":"1e369f08d03d187e708fecfe8fd69b4a2c750b8f2a730d6ebc1bfbc5c37d80c1","abstract_canon_sha256":"4e0b4b296b9a48a3de316dccd659fd6b9e0a4c60caf1d2631c931d4e4f447ba1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:44.773089Z","signature_b64":"yiwEmLuqjmwEt86dR71CiX53f0RhchQx/JzSSIK6OIL+qI6nTkAmMzDTuMrcSRgaTufZLC3QYnYONvPG/40dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44461ca4c7b7ac54fffeb94dce0923a768ed4b3cd27df6d2f480ec6ec4f721c5","last_reissued_at":"2026-07-05T09:52:44.772637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:44.772637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cijo Jose, Dahyun Kang, Daniel Li, Federico Baldassarre, Hu Xu, Huy V. Vo, Marc Szafraniec, Maxime Oquab, Micha\\\"el Ramamonjisoa, Oriane Sim\\'eoni, Patrick Labatut, Piotr Bojanowski, Th\\'eo Moutakanni, Timoth\\'ee Darcet","submitted_at":"2024-12-20T20:46:48Z","abstract_excerpt":"Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not readily aligned with language, hindering their adoption in open-vocabulary tasks. Our method, named dino.txt, unlocks this new ability for DINOv2, a widely used self-supervised visual encoder. We build upon the LiT training strategy, which trains a text encoder to align with a frozen vision model but leads to unsatisfactory results on dense tasks. We propose seve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16334","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/2412.16334/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":"2412.16334","created_at":"2026-07-05T09:52:44.772694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16334v1","created_at":"2026-07-05T09:52:44.772694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16334","created_at":"2026-07-05T09:52:44.772694+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRDBZJGHW6WF","created_at":"2026-07-05T09:52:44.772694+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRDBZJGHW6WFJ776","created_at":"2026-07-05T09:52:44.772694+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRDBZJGH","created_at":"2026-07-05T09:52:44.772694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06305","citing_title":"Exploring Image-Text Alignment for Radio Galaxy Morphologies","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5","json":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5.json","graph_json":"https://pith.science/api/pith-number/IRDBZJGHW6WFJ776XFG44CJDU5/graph.json","events_json":"https://pith.science/api/pith-number/IRDBZJGHW6WFJ776XFG44CJDU5/events.json","paper":"https://pith.science/paper/IRDBZJGH"},"agent_actions":{"view_html":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5","download_json":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5.json","view_paper":"https://pith.science/paper/IRDBZJGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16334&json=true","fetch_graph":"https://pith.science/api/pith-number/IRDBZJGHW6WFJ776XFG44CJDU5/graph.json","fetch_events":"https://pith.science/api/pith-number/IRDBZJGHW6WFJ776XFG44CJDU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5/action/storage_attestation","attest_author":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5/action/author_attestation","sign_citation":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5/action/citation_signature","submit_replication":"https://pith.science/pith/IRDBZJGHW6WFJ776XFG44CJDU5/action/replication_record"}},"created_at":"2026-07-05T09:52:44.772694+00:00","updated_at":"2026-07-05T09:52:44.772694+00:00"}