{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EOWT7VSRXKKZQO3YUPIYKI3GHS","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":"1ebe9376d201c4f5dd594b34ae58382230646d0bfbee989b375022e5dde42143","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:52:00Z","title_canon_sha256":"9acab81027911b516284fd465c1b05f15a461b6a4089da97d184adb13eda6220"},"schema_version":"1.0","source":{"id":"2412.04429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04429","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04429v1","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04429","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"EOWT7VSRXKKZ","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"EOWT7VSRXKKZQO3Y","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"EOWT7VSR","created_at":"2026-07-05T09:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:5f9c319e89d6da7670719260b8604f3c1f6f1de4309eacc7aa628491c82ea838","target":"graph","created_at":"2026-07-05T09:45:03Z","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/2412.04429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the highest similarity with the query image. While successful in some domains, this method struggles with identifying fine-grained entities as well as generalizing to unseen concepts that are not captured by the training distribution. Recent works attempt to mitigate these challenges by integrating category descriptions at test time, albeit yielding modest improveme","authors_text":"James Seale Smith, Junjiao Tian, Katherine Stevo, K J Joseph, Shaunak Halbe, Vineeth N Balasubramanian, Zsolt Kira","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:52:00Z","title":"Grounding Descriptions in Images informs Zero-Shot Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04429","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:bcfba2f510e8ec4be343e6c610660cfcfe8ed1fe683b6dd9ece4377eb1b139aa","target":"record","created_at":"2026-07-05T09:45:03Z","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":"1ebe9376d201c4f5dd594b34ae58382230646d0bfbee989b375022e5dde42143","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:52:00Z","title_canon_sha256":"9acab81027911b516284fd465c1b05f15a461b6a4089da97d184adb13eda6220"},"schema_version":"1.0","source":{"id":"2412.04429","kind":"arxiv","version":1}},"canonical_sha256":"23ad3fd651ba95983b78a3d18523663cb5db3c430479643cd9d8374869eddcc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23ad3fd651ba95983b78a3d18523663cb5db3c430479643cd9d8374869eddcc6","first_computed_at":"2026-07-05T09:45:03.813116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:03.813116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uVLog3FuviDCkLx7wdmxkAQ2EL/yYqqYEBMg/ProT5hAg2FxBXiFZKTnEdyhQOqeg+E+UR9xyOUUa2TSNLQlBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:03.813585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcfba2f510e8ec4be343e6c610660cfcfe8ed1fe683b6dd9ece4377eb1b139aa","sha256:5f9c319e89d6da7670719260b8604f3c1f6f1de4309eacc7aa628491c82ea838"],"state_sha256":"6b34581016cd38bc8273013513a85b35dd769baf662e7010d05d3ad231795584"}