{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CLTCYCQOUIDV4QOGKAVBU6YC2","short_pith_number":"pith:5CLTCYCQ","schema_version":"1.0","canonical_sha256":"e89731605075103af20e328150d3d8168eb5582e87dfc2cb0f38874164307997","source":{"kind":"arxiv","id":"2405.11301","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Canshi Wei","submitted_at":"2024-05-18T14:12:04Z","abstract_excerpt":"Fine-grained image classification, particularly in zero/few-shot scenarios, presents a significant challenge for vision-language models (VLMs), such as CLIP. These models often struggle with the nuanced task of distinguishing between semantically similar classes due to limitations in their pre-trained recipe, which lacks supervision signals for fine-grained categorization. This paper introduces CascadeVLM, an innovative framework that overcomes the constraints of previous CLIP-based methods by effectively leveraging the granular knowledge encapsulated within large vision-language models (LVLMs"},"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":"2405.11301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T14:12:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4f99ed6ff64586d1e1a244882443f72118d9b0ee43d7536930a6c400d65013ab","abstract_canon_sha256":"200a7066964ac786a8f0b294aca4d816e1d2e5ab3dfbc054e694add74b87742b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:36.790836Z","signature_b64":"gcLK7wD4Vh21ANkBBvD1p45U8gGeaLzuANL1CDLlVXIR1JK68bH73nL/Uf3mDRgc/50HCxnR2CsmppTrB9d+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e89731605075103af20e328150d3d8168eb5582e87dfc2cb0f38874164307997","last_reissued_at":"2026-07-05T08:20:36.790340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:36.790340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Canshi Wei","submitted_at":"2024-05-18T14:12:04Z","abstract_excerpt":"Fine-grained image classification, particularly in zero/few-shot scenarios, presents a significant challenge for vision-language models (VLMs), such as CLIP. These models often struggle with the nuanced task of distinguishing between semantically similar classes due to limitations in their pre-trained recipe, which lacks supervision signals for fine-grained categorization. This paper introduces CascadeVLM, an innovative framework that overcomes the constraints of previous CLIP-based methods by effectively leveraging the granular knowledge encapsulated within large vision-language models (LVLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11301","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/2405.11301/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":"2405.11301","created_at":"2026-07-05T08:20:36.790413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11301v1","created_at":"2026-07-05T08:20:36.790413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11301","created_at":"2026-07-05T08:20:36.790413+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CLTCYCQOUID","created_at":"2026-07-05T08:20:36.790413+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CLTCYCQOUIDV4QO","created_at":"2026-07-05T08:20:36.790413+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CLTCYCQ","created_at":"2026-07-05T08:20:36.790413+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/5CLTCYCQOUIDV4QOGKAVBU6YC2","json":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2.json","graph_json":"https://pith.science/api/pith-number/5CLTCYCQOUIDV4QOGKAVBU6YC2/graph.json","events_json":"https://pith.science/api/pith-number/5CLTCYCQOUIDV4QOGKAVBU6YC2/events.json","paper":"https://pith.science/paper/5CLTCYCQ"},"agent_actions":{"view_html":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2","download_json":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2.json","view_paper":"https://pith.science/paper/5CLTCYCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11301&json=true","fetch_graph":"https://pith.science/api/pith-number/5CLTCYCQOUIDV4QOGKAVBU6YC2/graph.json","fetch_events":"https://pith.science/api/pith-number/5CLTCYCQOUIDV4QOGKAVBU6YC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2/action/storage_attestation","attest_author":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2/action/author_attestation","sign_citation":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2/action/citation_signature","submit_replication":"https://pith.science/pith/5CLTCYCQOUIDV4QOGKAVBU6YC2/action/replication_record"}},"created_at":"2026-07-05T08:20:36.790413+00:00","updated_at":"2026-07-05T08:20:36.790413+00:00"}