{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7RS74SAMGDFXWIXYD5HRTI6KKZ","short_pith_number":"pith:7RS74SAM","schema_version":"1.0","canonical_sha256":"fc65fe480c30cb7b22f81f4f19a3ca567f4ad2c0927d397bf8fff2f6bcfbfc26","source":{"kind":"arxiv","id":"2201.08625","version":1},"attestation_state":"computed","paper":{"title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Attila Lengyel, Davide Zambrano, Jan van Gemert, Marcos Baptista Rios, Nergis Tomen, Osman Semih Kayhan, Robert-Jan Bruintjes","submitted_at":"2022-01-21T10:20:52Z","abstract_excerpt":"The second edition of the \"VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning\" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks. To encourage new and creative ideas on incorporating relevant inductive biases to improve the data efficiency of deep learning models, we prohibited the use of pre-trained checkpoints and other transfer learning techniques. The provided baselines are outperformed by a large margin in all five challenges, mainly thanks to extensive data"},"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":"2201.08625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-21T10:20:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"015e1cf5403c44ea1b387eb71ba13c1a70abae0a57444ffde8231696b108eec7","abstract_canon_sha256":"9f53efd72261e930540137bce3cfa6ad4f7d72891fe3bb8503027fb6da587138"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:30.501858Z","signature_b64":"xdv56qRdMOJ/5BKUmmv7g4A+ClwFuh0vfTLgT0+f+6kgLZvJfiHvt+JCFnuSp1CPqLTRJ9JaOzhaf3ZlZ51iBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc65fe480c30cb7b22f81f4f19a3ca567f4ad2c0927d397bf8fff2f6bcfbfc26","last_reissued_at":"2026-07-05T03:50:30.501497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:30.501497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Attila Lengyel, Davide Zambrano, Jan van Gemert, Marcos Baptista Rios, Nergis Tomen, Osman Semih Kayhan, Robert-Jan Bruintjes","submitted_at":"2022-01-21T10:20:52Z","abstract_excerpt":"The second edition of the \"VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning\" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks. To encourage new and creative ideas on incorporating relevant inductive biases to improve the data efficiency of deep learning models, we prohibited the use of pre-trained checkpoints and other transfer learning techniques. The provided baselines are outperformed by a large margin in all five challenges, mainly thanks to extensive data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08625","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/2201.08625/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":"2201.08625","created_at":"2026-07-05T03:50:30.501568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08625v1","created_at":"2026-07-05T03:50:30.501568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08625","created_at":"2026-07-05T03:50:30.501568+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RS74SAMGDFX","created_at":"2026-07-05T03:50:30.501568+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RS74SAMGDFXWIXY","created_at":"2026-07-05T03:50:30.501568+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RS74SAM","created_at":"2026-07-05T03:50:30.501568+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/7RS74SAMGDFXWIXYD5HRTI6KKZ","json":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ.json","graph_json":"https://pith.science/api/pith-number/7RS74SAMGDFXWIXYD5HRTI6KKZ/graph.json","events_json":"https://pith.science/api/pith-number/7RS74SAMGDFXWIXYD5HRTI6KKZ/events.json","paper":"https://pith.science/paper/7RS74SAM"},"agent_actions":{"view_html":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ","download_json":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ.json","view_paper":"https://pith.science/paper/7RS74SAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08625&json=true","fetch_graph":"https://pith.science/api/pith-number/7RS74SAMGDFXWIXYD5HRTI6KKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7RS74SAMGDFXWIXYD5HRTI6KKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ/action/storage_attestation","attest_author":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ/action/author_attestation","sign_citation":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ/action/citation_signature","submit_replication":"https://pith.science/pith/7RS74SAMGDFXWIXYD5HRTI6KKZ/action/replication_record"}},"created_at":"2026-07-05T03:50:30.501568+00:00","updated_at":"2026-07-05T03:50:30.501568+00:00"}