{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VHKEUZ3IXPWC47FBKG3Q5PAIQV","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":"44ced6aa60d597cb50792d3a19e7842afcfdf86471a96419bf6386deb79fbfd0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T09:26:16Z","title_canon_sha256":"5e0b1669158c91ef7efc2a3a42ac10d4b48af8a06f3d4bfab51d06a35b80f7ee"},"schema_version":"1.0","source":{"id":"2604.11225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11225","created_at":"2026-06-26T01:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11225v1","created_at":"2026-06-26T01:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11225","created_at":"2026-06-26T01:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"VHKEUZ3IXPWC","created_at":"2026-06-26T01:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"VHKEUZ3IXPWC47FB","created_at":"2026-06-26T01:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"VHKEUZ3I","created_at":"2026-06-26T01:15:51Z"}],"graph_snapshots":[{"event_id":"sha256:10159ab41d29f69ad7599e688ab1d36868308f0a0e1db9f41199c7ee630d8104","target":"graph","created_at":"2026-06-26T01:15:51Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"under prompt-only zero-shot inference, current open-source VLMs remain far behind classic supervised ISLR classifiers by a wide margin. However, follow-up experiments reveal that these models capture partial visual-semantic alignment between signs and text descriptions. Larger proprietary models achieve substantially higher accuracy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen prompts, WLASL300 benchmark splits, and evaluation protocol provide an unbiased test of zero-shot capability without hidden advantages from prompt engineering or dataset characteristics."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Zero-shot VLM evaluation on WLASL300 reveals open-source models lag far behind supervised ISLR baselines, but proprietary models improve with scale and exhibit some visual-semantic alignment."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Open-source VLMs lag far behind supervised classifiers in zero-shot sign language recognition but capture partial visual-semantic alignment."}],"snapshot_sha256":"47c486ded64478a4b522fc93a6e852140e5bba4ec15f99554bca667f72c0cfc1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Vision Language Models (VLMs) have demonstrated strong performance across a wide range of multimodal reasoning tasks. This raises the question of whether such general-purpose models can also address specialized visual recognition problems such as isolated sign language recognition (ISLR) without task-specific training. In this work, we investigate the capability of modern VLMs to perform ISLR in a zero-shot setting. We evaluate several open-source and proprietary VLMs on the WLASL300 benchmark. Our experiments show that, under prompt-only zero-shot inference, current open-source VLMs re","authors_text":"Ivan Gruber, Jakub Honzik, Marek Hruz, Tomas Zelezny, Vaclav Javorek","cross_cats":["cs.CL"],"headline":"Open-source VLMs lag far behind supervised classifiers in zero-shot sign language recognition but capture partial visual-semantic alignment.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T09:26:16Z","title":"Sign Language Recognition in the Age of LLMs"},"references":{"count":44,"internal_anchors":2,"resolved_work":44,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Flamingo: a visual language model for few- shot learning","work_id":"8077b03e-3b58-4984-9d17-7025a3593594","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Pyav: Pythonic bindings for ffm- peg.https://github.com/PyAV-Org/PyAV","work_id":"88b9e280-46e2-47f8-a71f-ffe11a16c2fe","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Language models are few-shot learn- ers.Advances in neural information processing sys- tems, 33:1877–1901","work_id":"c4b7fbe8-38ff-4f9c-921c-223ff3a20fda","year":1901},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Pillow (pil fork) documentation","work_id":"9253d432-575e-4e41-9d6f-fb7b47e99862","year":2015},{"cited_arxiv_id":"2505.14683","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Emerging Properties in Unified Multimodal Pretraining","work_id":"e0cfd82c-f5d4-44fd-b531-ec73ab0a805b","year":2025}],"snapshot_sha256":"ed46b9d1b80be4198b042f54434acf306f0e168166e1dffe575823d5a284f375"},"source":{"id":"2604.11225","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-10T15:31:21.413668Z","id":"46a620be-b5fe-4623-91aa-1020545e9560","model_set":{"reader":"grok-4.3"},"one_line_summary":"Zero-shot VLM evaluation on WLASL300 reveals open-source models lag far behind supervised ISLR baselines, but proprietary models improve with scale and exhibit some visual-semantic alignment.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Open-source VLMs lag far behind supervised classifiers in zero-shot sign language recognition but capture partial visual-semantic alignment.","strongest_claim":"under prompt-only zero-shot inference, current open-source VLMs remain far behind classic supervised ISLR classifiers by a wide margin. However, follow-up experiments reveal that these models capture partial visual-semantic alignment between signs and text descriptions. Larger proprietary models achieve substantially higher accuracy.","weakest_assumption":"That the chosen prompts, WLASL300 benchmark splits, and evaluation protocol provide an unbiased test of zero-shot capability without hidden advantages from prompt engineering or dataset characteristics."}},"verdict_id":"46a620be-b5fe-4623-91aa-1020545e9560"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4a852fdc08faaf1eb2eb5a03e5c2077463760836b4206094730e5ec723a2817d","target":"record","created_at":"2026-06-26T01:15:51Z","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":"44ced6aa60d597cb50792d3a19e7842afcfdf86471a96419bf6386deb79fbfd0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T09:26:16Z","title_canon_sha256":"5e0b1669158c91ef7efc2a3a42ac10d4b48af8a06f3d4bfab51d06a35b80f7ee"},"schema_version":"1.0","source":{"id":"2604.11225","kind":"arxiv","version":1}},"canonical_sha256":"a9d44a6768bbec2e7ca151b70ebc08857a337829f40148218e7a0a63763d2e35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9d44a6768bbec2e7ca151b70ebc08857a337829f40148218e7a0a63763d2e35","first_computed_at":"2026-06-26T01:15:51.643721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:51.643721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OYp8mqCZYG8hwhqDzVwYQRIWtdMMl3HQq0cs2yJAKe64Y/CpbQDLIaFgq3j1Vnks4F5aAK1vnCkfwXqWaF53Cg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:51.644096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a852fdc08faaf1eb2eb5a03e5c2077463760836b4206094730e5ec723a2817d","sha256:10159ab41d29f69ad7599e688ab1d36868308f0a0e1db9f41199c7ee630d8104"],"state_sha256":"abe6539c2323c51eee86b915a045fd5569276e2d70e9aa0d34237319b281330b"}