{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SLFF4WIDEHVUERWAEBSP2QPPK6","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":"56f0aca3def6f8797af77a57ed78010655f2767596b3f61a7046c778741c3c66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T19:30:03Z","title_canon_sha256":"c415eac432d9c30c382a91bae877910a08633a59ea50a4d3fbea16644da6b941"},"schema_version":"1.0","source":{"id":"2608.00235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00235","created_at":"2026-08-04T00:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00235v1","created_at":"2026-08-04T00:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00235","created_at":"2026-08-04T00:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"SLFF4WIDEHVU","created_at":"2026-08-04T00:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"SLFF4WIDEHVUERWA","created_at":"2026-08-04T00:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"SLFF4WID","created_at":"2026-08-04T00:34:27Z"}],"graph_snapshots":[{"event_id":"sha256:a05cedf6ef9f349db4152ad43a4f8e73162c3fb45c8183c7b2998a4542a1bb6e","target":"graph","created_at":"2026-08-04T00:34:27Z","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/2608.00235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language translation task, where we identify a key failure mode of existing VLMbased translators: poor spatial-temporal visual grounding. In particular, we find that standard next-token cross-entropy does not directly provide signal for where and when the model should attend, causing models to overlook sign-relevant regions and frames. To address this challenge, we propose AttnSign, a VLM-based spatial-temporal attention steering framework for sign lan","authors_text":"Annemarie D. Ross, Guohao Sun, Meibo Hu, Sheng Li, Zhiqiang Tao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T19:30:03Z","title":"Attention-Steered Vision-Language Models for Sign Language Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00235","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:bc7f3dcde5bda39b1bdcc70cb5b936d2ad12c9dcacf9e1a4c1df4fcc504be54e","target":"record","created_at":"2026-08-04T00:34:27Z","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":"56f0aca3def6f8797af77a57ed78010655f2767596b3f61a7046c778741c3c66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T19:30:03Z","title_canon_sha256":"c415eac432d9c30c382a91bae877910a08633a59ea50a4d3fbea16644da6b941"},"schema_version":"1.0","source":{"id":"2608.00235","kind":"arxiv","version":1}},"canonical_sha256":"92ca5e590321eb4246c02064fd41ef579cf93d8cb0d003616717c3513188b73e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92ca5e590321eb4246c02064fd41ef579cf93d8cb0d003616717c3513188b73e","first_computed_at":"2026-08-04T00:34:27.215806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:34:27.215806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"596PWdGdcQ/g7QFoHKdzlVcNgFU5RZ38N68fmDQQAg1deY1GIEaKycXqQ/CV/GFwCfAprc6eCGvemKe7VnuOAw==","signature_status":"signed_v1","signed_at":"2026-08-04T00:34:27.217262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc7f3dcde5bda39b1bdcc70cb5b936d2ad12c9dcacf9e1a4c1df4fcc504be54e","sha256:a05cedf6ef9f349db4152ad43a4f8e73162c3fb45c8183c7b2998a4542a1bb6e"],"state_sha256":"563ebd5ef420a5ad84d254e9834e755ba080ce55cd2f3503beea7c3fdaad54ac"}