{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5CLTCYCQOUIDV4QOGKAVBU6YC2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"200a7066964ac786a8f0b294aca4d816e1d2e5ab3dfbc054e694add74b87742b","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T14:12:04Z","title_canon_sha256":"4f99ed6ff64586d1e1a244882443f72118d9b0ee43d7536930a6c400d65013ab"},"schema_version":"1.0","source":{"id":"2405.11301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11301","created_at":"2026-07-05T08:20:36Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11301v1","created_at":"2026-07-05T08:20:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11301","created_at":"2026-07-05T08:20:36Z"},{"alias_kind":"pith_short_12","alias_value":"5CLTCYCQOUID","created_at":"2026-07-05T08:20:36Z"},{"alias_kind":"pith_short_16","alias_value":"5CLTCYCQOUIDV4QO","created_at":"2026-07-05T08:20:36Z"},{"alias_kind":"pith_short_8","alias_value":"5CLTCYCQ","created_at":"2026-07-05T08:20:36Z"}],"graph_snapshots":[{"event_id":"sha256:f081ee61466b9732bf1789198dd3be9b6249ed58d25d6c60bd9fb78425b79c86","target":"graph","created_at":"2026-07-05T08:20:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.11301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Canshi Wei","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T14:12:04Z","title":"Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11301","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e18d3da10a9019c262904bbe313ea24445d15cc030f79f9a01b746c7533b647","target":"record","created_at":"2026-07-05T08:20:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"200a7066964ac786a8f0b294aca4d816e1d2e5ab3dfbc054e694add74b87742b","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-18T14:12:04Z","title_canon_sha256":"4f99ed6ff64586d1e1a244882443f72118d9b0ee43d7536930a6c400d65013ab"},"schema_version":"1.0","source":{"id":"2405.11301","kind":"arxiv","version":1}},"canonical_sha256":"e89731605075103af20e328150d3d8168eb5582e87dfc2cb0f38874164307997","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e89731605075103af20e328150d3d8168eb5582e87dfc2cb0f38874164307997","first_computed_at":"2026-07-05T08:20:36.790340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:36.790340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gcLK7wD4Vh21ANkBBvD1p45U8gGeaLzuANL1CDLlVXIR1JK68bH73nL/Uf3mDRgc/50HCxnR2CsmppTrB9d+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:36.790836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e18d3da10a9019c262904bbe313ea24445d15cc030f79f9a01b746c7533b647","sha256:f081ee61466b9732bf1789198dd3be9b6249ed58d25d6c60bd9fb78425b79c86"],"state_sha256":"57c67e9fb37afff1dffe89ecb99d9c582383c01392818cae025aadbdfb1fae9f"}