{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SD55WV7DNIZA7AFFUTS73RTFBX","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":"a8c2814e5205838a493bc4a3f593b36792aa0c14c9c2e477bceae3bd7e1b27c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-29T22:08:45Z","title_canon_sha256":"27b451f0e687f4c6eb7ed446e8407db49db550496e9e4a70aa8e5451b9e0c05d"},"schema_version":"1.0","source":{"id":"2604.27232","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27232","created_at":"2026-06-03T01:05:50Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27232v2","created_at":"2026-06-03T01:05:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27232","created_at":"2026-06-03T01:05:50Z"},{"alias_kind":"pith_short_12","alias_value":"SD55WV7DNIZA","created_at":"2026-06-03T01:05:50Z"},{"alias_kind":"pith_short_16","alias_value":"SD55WV7DNIZA7AFF","created_at":"2026-06-03T01:05:50Z"},{"alias_kind":"pith_short_8","alias_value":"SD55WV7D","created_at":"2026-06-03T01:05:50Z"}],"graph_snapshots":[{"event_id":"sha256:8fa0fffdc1df02c982b041a2cbb79509968d8fe35291a657319515307e80b285","target":"graph","created_at":"2026-06-03T01:05:50Z","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":"Our results show that, while the model performs above chance level on most of the phenomena, it relies strongly on manual cues while often missing crucial non-manual cues."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the minimal translation pairs in ASL-MTP cleanly isolate individual linguistic phenomena without confounding interactions between manual and non-manual channels, and that ablating input cues during training and inference produces a faithful measure of the model's internal reliance rather than an artifact of the ablation procedure."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A new ASL minimal pairs benchmark shows state-of-the-art sign language translation models perform above chance on many phenomena but rely heavily on manual cues while missing non-manual ones."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sign language translation models rely primarily on manual hand cues and miss key non-manual cues from the face and body."}],"snapshot_sha256":"75a095323dd2240cbac787b6629a6519f85f82b4fbd1a4ea860a8b0b85ae3ca5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T22:41:46.642627Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:26:31.500036Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27232/integrity.json","findings":[],"snapshot_sha256":"4f706f2074c2855ad30355d6719fa5352c4e54c0540f36830ca106ae2d1896ff","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models of sign language have historically lagged behind those for spoken language (text and speech). Recent work has greatly improved their performance on tasks like sign language translation and isolated sign recognition. However, it remains unclear to what extent existing models capture various linguistic phenomena of sign language, and how well they use cues from the multiple articulators used in sign language (hands, upper body, face). We introduce a new benchmark dataset for American Sign Language, ASL Minimal Translation Pairs (ASL-MTP), divided into multiple types of sign language pheno","authors_text":"Diane Brentari, Greg Shakhnarovich, Kanishka Misra, Karen Livescu, Serpil Karab\\\"ukl\\\"u, Shester Gueuwou","cross_cats":[],"headline":"Sign language translation models rely primarily on manual hand cues and miss key non-manual cues from the face and body.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-29T22:08:45Z","title":"Targeted Linguistic Analysis of Sign Language Models with Minimal Translation Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27232","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T08:15:10.897168Z","id":"925c3c4d-1aec-46b5-9505-6d07c0299d12","model_set":{"reader":"grok-4.3"},"one_line_summary":"A new ASL minimal pairs benchmark shows state-of-the-art sign language translation models perform above chance on many phenomena but rely heavily on manual cues while missing non-manual ones.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sign language translation models rely primarily on manual hand cues and miss key non-manual cues from the face and body.","strongest_claim":"Our results show that, while the model performs above chance level on most of the phenomena, it relies strongly on manual cues while often missing crucial non-manual cues.","weakest_assumption":"That the minimal translation pairs in ASL-MTP cleanly isolate individual linguistic phenomena without confounding interactions between manual and non-manual channels, and that ablating input cues during training and inference produces a faithful measure of the model's internal reliance rather than an artifact of the ablation procedure."}},"verdict_id":"925c3c4d-1aec-46b5-9505-6d07c0299d12"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1b527fe5bfc74e0fe1eb5765b6bce865b9aba691a3547807da97ce180f864a1d","target":"record","created_at":"2026-06-03T01:05:50Z","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":"a8c2814e5205838a493bc4a3f593b36792aa0c14c9c2e477bceae3bd7e1b27c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-29T22:08:45Z","title_canon_sha256":"27b451f0e687f4c6eb7ed446e8407db49db550496e9e4a70aa8e5451b9e0c05d"},"schema_version":"1.0","source":{"id":"2604.27232","kind":"arxiv","version":2}},"canonical_sha256":"90fbdb57e36a320f80a5a4e5fdc6650de4941f627e2e93d2ed7023694919f0ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90fbdb57e36a320f80a5a4e5fdc6650de4941f627e2e93d2ed7023694919f0ad","first_computed_at":"2026-06-03T01:05:50.736090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:50.736090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UPnAoajoQ363O3xSvCkqUoUxaOs/eh/4AUgupfky+iaKOFaYTsImRx+m5zgipFZf4dyqvL5dVmZz63/eOwlJCQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:50.736509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27232","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b527fe5bfc74e0fe1eb5765b6bce865b9aba691a3547807da97ce180f864a1d","sha256:8fa0fffdc1df02c982b041a2cbb79509968d8fe35291a657319515307e80b285"],"state_sha256":"b2504a0244f2b24cf0da38aa8ef20bd8461e92d3c2162e17c4a5884637a65ba7"}