{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EYKWFBUF2ORUMVIX23SHW5HPDL","short_pith_number":"pith:EYKWFBUF","schema_version":"1.0","canonical_sha256":"2615628685d3a3465517d6e47b74ef1ac04beea8e0ee2c206d8cb197dcc89cf2","source":{"kind":"arxiv","id":"2605.18700","version":1},"attestation_state":"computed","paper":{"title":"A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Augusto Christian Surya, Bo-Cheng Lai, Edwin Arkel Rios, Fernando Mikael, Kisoon Jang, Mary Madeline Nicole, Min-Chun Hu, Oswin Gosal","submitted_at":"2026-05-18T17:36:30Z","abstract_excerpt":"Prior work on fine-grained image recognition (FGIR) has established the importance of the backbone selection, but has neglected the accuracy-vs-cost trade-offs under different training and evaluation settings. In this work we conduct a large-scale study with over 2000 experiments across 6 training and evaluation settings, 9 pretrained backbones, and 17 datasets. Preliminary observations on the effectiveness of data augmentation for fine-grained training motivate us to extend Counterfactual Attention Learning (CAL), a state-of-the-art method based on data-aware cropping and masking augmentation"},"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":"2605.18700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"e712ff88454fd60157afd9a270f87109b06994cdd2ad3da90776c2058de95535","abstract_canon_sha256":"64ad9b58091cae080d16a62944a3709364eee5ec3746036a38a15ce371c7f9ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:15.738299Z","signature_b64":"kaOnUAegsZ7wKoE1GmtxtasnQbF9+B7sKJ2aD59J4CEfUQFpMHmenSJxzNMaEKL61X+NnCCj4Qiu6FfK96eaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2615628685d3a3465517d6e47b74ef1ac04beea8e0ee2c206d8cb197dcc89cf2","last_reissued_at":"2026-05-20T00:06:15.737491Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:15.737491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Augusto Christian Surya, Bo-Cheng Lai, Edwin Arkel Rios, Fernando Mikael, Kisoon Jang, Mary Madeline Nicole, Min-Chun Hu, Oswin Gosal","submitted_at":"2026-05-18T17:36:30Z","abstract_excerpt":"Prior work on fine-grained image recognition (FGIR) has established the importance of the backbone selection, but has neglected the accuracy-vs-cost trade-offs under different training and evaluation settings. In this work we conduct a large-scale study with over 2000 experiments across 6 training and evaluation settings, 9 pretrained backbones, and 17 datasets. Preliminary observations on the effectiveness of data augmentation for fine-grained training motivate us to extend Counterfactual Attention Learning (CAL), a state-of-the-art method based on data-aware cropping and masking augmentation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18700","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/2605.18700/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.078964Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"132e1ff490fc60305df2659379f37f34ec863daf577a3ae44179a254aa9b6e27"},"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":"2605.18700","created_at":"2026-05-20T00:06:15.737632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18700v1","created_at":"2026-05-20T00:06:15.737632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18700","created_at":"2026-05-20T00:06:15.737632+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYKWFBUF2ORU","created_at":"2026-05-20T00:06:15.737632+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYKWFBUF2ORUMVIX","created_at":"2026-05-20T00:06:15.737632+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYKWFBUF","created_at":"2026-05-20T00:06:15.737632+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/EYKWFBUF2ORUMVIX23SHW5HPDL","json":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL.json","graph_json":"https://pith.science/api/pith-number/EYKWFBUF2ORUMVIX23SHW5HPDL/graph.json","events_json":"https://pith.science/api/pith-number/EYKWFBUF2ORUMVIX23SHW5HPDL/events.json","paper":"https://pith.science/paper/EYKWFBUF"},"agent_actions":{"view_html":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL","download_json":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL.json","view_paper":"https://pith.science/paper/EYKWFBUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18700&json=true","fetch_graph":"https://pith.science/api/pith-number/EYKWFBUF2ORUMVIX23SHW5HPDL/graph.json","fetch_events":"https://pith.science/api/pith-number/EYKWFBUF2ORUMVIX23SHW5HPDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL/action/storage_attestation","attest_author":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL/action/author_attestation","sign_citation":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL/action/citation_signature","submit_replication":"https://pith.science/pith/EYKWFBUF2ORUMVIX23SHW5HPDL/action/replication_record"}},"created_at":"2026-05-20T00:06:15.737632+00:00","updated_at":"2026-05-20T00:06:15.737632+00:00"}