{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HFXSGFJLDOKA2QR26O7ESV4JIL","short_pith_number":"pith:HFXSGFJL","schema_version":"1.0","canonical_sha256":"396f23152b1b940d423af3be49578942cca0f5cffbbce1ed8d40e65e244bb29c","source":{"kind":"arxiv","id":"2606.05107","version":1},"attestation_state":"computed","paper":{"title":"Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Camille Couprie, Elouan Gard\\`es, Huy V. Vo, Kartik Ahuja, Lo\\\"ic Landrieu, Piotr Bojanowski, Seung Eun Yi, Th\\'eo Moutakanni, Wolfgang M. Pernice","submitted_at":"2026-06-03T17:10:11Z","abstract_excerpt":"We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to these settings: labels are scarce, and task-specific training can collapse the model's generality and hurt robustness. We instead leverage metadata to adapt representations to new domains in a self-supervised manner. Our method, FINO, combines a standard self-supervised objective with flexible metadata guidance that handles both highly granular discrete metadata and continuous metadata. It encourages the representation"},"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":"2606.05107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T17:10:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da8efb371249144f6148fdf1e82856c64a22b32a217f962f9305f686d936ee2d","abstract_canon_sha256":"8b431b8c956afeeed4ff2837550ca909f82761a1b90f7cc64f5460f9d021869b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:06.603531Z","signature_b64":"o23XNczKdBz5nK86OxAyeRmLyMX4a9ToZgCr1DnVbwhQPKX/62x7dUYfILuQABPxsvwzJZWVR1O+v675CgCDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"396f23152b1b940d423af3be49578942cca0f5cffbbce1ed8d40e65e244bb29c","last_reissued_at":"2026-06-04T01:10:06.603049Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:06.603049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Camille Couprie, Elouan Gard\\`es, Huy V. Vo, Kartik Ahuja, Lo\\\"ic Landrieu, Piotr Bojanowski, Seung Eun Yi, Th\\'eo Moutakanni, Wolfgang M. Pernice","submitted_at":"2026-06-03T17:10:11Z","abstract_excerpt":"We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to these settings: labels are scarce, and task-specific training can collapse the model's generality and hurt robustness. We instead leverage metadata to adapt representations to new domains in a self-supervised manner. Our method, FINO, combines a standard self-supervised objective with flexible metadata guidance that handles both highly granular discrete metadata and continuous metadata. It encourages the representation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05107","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/2606.05107/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":"2606.05107","created_at":"2026-06-04T01:10:06.603113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05107v1","created_at":"2026-06-04T01:10:06.603113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05107","created_at":"2026-06-04T01:10:06.603113+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFXSGFJLDOKA","created_at":"2026-06-04T01:10:06.603113+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFXSGFJLDOKA2QR2","created_at":"2026-06-04T01:10:06.603113+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFXSGFJL","created_at":"2026-06-04T01:10:06.603113+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/HFXSGFJLDOKA2QR26O7ESV4JIL","json":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL.json","graph_json":"https://pith.science/api/pith-number/HFXSGFJLDOKA2QR26O7ESV4JIL/graph.json","events_json":"https://pith.science/api/pith-number/HFXSGFJLDOKA2QR26O7ESV4JIL/events.json","paper":"https://pith.science/paper/HFXSGFJL"},"agent_actions":{"view_html":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL","download_json":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL.json","view_paper":"https://pith.science/paper/HFXSGFJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05107&json=true","fetch_graph":"https://pith.science/api/pith-number/HFXSGFJLDOKA2QR26O7ESV4JIL/graph.json","fetch_events":"https://pith.science/api/pith-number/HFXSGFJLDOKA2QR26O7ESV4JIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL/action/storage_attestation","attest_author":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL/action/author_attestation","sign_citation":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL/action/citation_signature","submit_replication":"https://pith.science/pith/HFXSGFJLDOKA2QR26O7ESV4JIL/action/replication_record"}},"created_at":"2026-06-04T01:10:06.603113+00:00","updated_at":"2026-06-04T01:10:06.603113+00:00"}