{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:57BIL6CJBJPJ2RAQXBPHMWTPTT","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":"74ac7ffd0c512b49e1aeadd6bf5befbd447ec2d2757bb734aa8d190a7413af65","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T12:34:21Z","title_canon_sha256":"cf579b4525a43bfa80ebe4ab94285a7e33ad02a48090a7e3eb413458df28985b"},"schema_version":"1.0","source":{"id":"2409.01835","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01835","created_at":"2026-07-05T09:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01835v2","created_at":"2026-07-05T09:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01835","created_at":"2026-07-05T09:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"57BIL6CJBJPJ","created_at":"2026-07-05T09:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"57BIL6CJBJPJ2RAQ","created_at":"2026-07-05T09:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"57BIL6CJ","created_at":"2026-07-05T09:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:00dffa2b3c774a84da74c1361cedb34dfad89fde7c9f50c17761d0a6b529b551","target":"graph","created_at":"2026-07-05T09:04:40Z","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/2409.01835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models trained on one domain do not generalize well on a different domain without fine-tuning. We attribute these to the limitations of the VLM's semantic representations and attempt to improve their fine-grained visual awareness using generative modeling. Specifically, we propose two novel methods: Generative Class Prompt Learning (GCPL) and Contrastive Multi-class Prom","authors_text":"Emanuele Vivoli, Josep Llad\\'os, Sanket Biswas, Soumitri Chattopadhyay","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T12:34:21Z","title":"Towards Generative Class Prompt Learning for Fine-grained Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01835","kind":"arxiv","version":2},"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":"sha256:46b469f1033409176dd9887ff387da3da0a2bf51bfa8ccf640079942cbfaf3bb","target":"record","created_at":"2026-07-05T09:04:40Z","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":"74ac7ffd0c512b49e1aeadd6bf5befbd447ec2d2757bb734aa8d190a7413af65","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T12:34:21Z","title_canon_sha256":"cf579b4525a43bfa80ebe4ab94285a7e33ad02a48090a7e3eb413458df28985b"},"schema_version":"1.0","source":{"id":"2409.01835","kind":"arxiv","version":2}},"canonical_sha256":"efc285f8490a5e9d4410b85e765a6f9cf5deaa74eca29246998065b7815a5fc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efc285f8490a5e9d4410b85e765a6f9cf5deaa74eca29246998065b7815a5fc3","first_computed_at":"2026-07-05T09:04:40.295636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:40.295636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I69HoboJurm/h6YG0Tvca9Xl5ZA3yNp75ReLKqLcVOhIm2RbfxxAc1MkK+pFdPtDwOEscKCGWev0gTHuLdbCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:40.296025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01835","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46b469f1033409176dd9887ff387da3da0a2bf51bfa8ccf640079942cbfaf3bb","sha256:00dffa2b3c774a84da74c1361cedb34dfad89fde7c9f50c17761d0a6b529b551"],"state_sha256":"53b201dac7c53134418b600323e941b8fdadca91a3b432ca13389e4a486662ca"}