{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XREOZQIUUR5MZ2ABJOXU7IPTPR","short_pith_number":"pith:XREOZQIU","schema_version":"1.0","canonical_sha256":"bc48ecc114a47acce8014baf4fa1f37c55ced10d18bad189c2783cada5ed9505","source":{"kind":"arxiv","id":"2203.02751","version":1},"attestation_state":"computed","paper":{"title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wen, Jia Sun, Qishuai Diao, Yi Jiang, Zehuan Yuan","submitted_at":"2022-03-05T14:12:25Z","abstract_excerpt":"Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated learning pipelines to tackle this task. However, visual information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Nowadays, the meta-information (e.g., spatio-temporal prior, attribute, and text description) usually appears along with the images. This inspires us to ask the question: Is it possible to use a unified and simple fr"},"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":"2203.02751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-05T14:12:25Z","cross_cats_sorted":[],"title_canon_sha256":"b610ab91c3bdaec4626ce0f924c2338cb504f9335fd5afc559846668e44fceb0","abstract_canon_sha256":"e4cbe4d2b54e15124cd2bf174d470a7ec2c74da0aeefeb213284680b0d90e5e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:26.978361Z","signature_b64":"57Qj1JO1uqF763pzeq5rhAckZPyRkPyKbreMxRdPutG00Lhmln1+BVDZZLDreD8bGAFJw26rRj0kOTTMPZ+cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc48ecc114a47acce8014baf4fa1f37c55ced10d18bad189c2783cada5ed9505","last_reissued_at":"2026-07-05T04:02:26.977947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:26.977947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wen, Jia Sun, Qishuai Diao, Yi Jiang, Zehuan Yuan","submitted_at":"2022-03-05T14:12:25Z","abstract_excerpt":"Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated learning pipelines to tackle this task. However, visual information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Nowadays, the meta-information (e.g., spatio-temporal prior, attribute, and text description) usually appears along with the images. This inspires us to ask the question: Is it possible to use a unified and simple fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02751","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/2203.02751/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":"2203.02751","created_at":"2026-07-05T04:02:26.978006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02751v1","created_at":"2026-07-05T04:02:26.978006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02751","created_at":"2026-07-05T04:02:26.978006+00:00"},{"alias_kind":"pith_short_12","alias_value":"XREOZQIUUR5M","created_at":"2026-07-05T04:02:26.978006+00:00"},{"alias_kind":"pith_short_16","alias_value":"XREOZQIUUR5MZ2AB","created_at":"2026-07-05T04:02:26.978006+00:00"},{"alias_kind":"pith_short_8","alias_value":"XREOZQIU","created_at":"2026-07-05T04:02:26.978006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19053","citing_title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14988","citing_title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR","json":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR.json","graph_json":"https://pith.science/api/pith-number/XREOZQIUUR5MZ2ABJOXU7IPTPR/graph.json","events_json":"https://pith.science/api/pith-number/XREOZQIUUR5MZ2ABJOXU7IPTPR/events.json","paper":"https://pith.science/paper/XREOZQIU"},"agent_actions":{"view_html":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR","download_json":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR.json","view_paper":"https://pith.science/paper/XREOZQIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02751&json=true","fetch_graph":"https://pith.science/api/pith-number/XREOZQIUUR5MZ2ABJOXU7IPTPR/graph.json","fetch_events":"https://pith.science/api/pith-number/XREOZQIUUR5MZ2ABJOXU7IPTPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR/action/storage_attestation","attest_author":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR/action/author_attestation","sign_citation":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR/action/citation_signature","submit_replication":"https://pith.science/pith/XREOZQIUUR5MZ2ABJOXU7IPTPR/action/replication_record"}},"created_at":"2026-07-05T04:02:26.978006+00:00","updated_at":"2026-07-05T04:02:26.978006+00:00"}