{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7RJIJKGFTWKBFSPX2XN7QKC5HZ","short_pith_number":"pith:7RJIJKGF","schema_version":"1.0","canonical_sha256":"fc5284a8c59d9412c9f7d5dbf8285d3e6867acbbb281e16be2741f5ee40247cb","source":{"kind":"arxiv","id":"2607.09126","version":1},"attestation_state":"computed","paper":{"title":"VTaMo: Video-Text Alignment Model for Sign Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aoxiang Yang, Haomian Huang, Junyi Hu, Yi Fang, Zhewen He","submitted_at":"2026-07-10T06:30:50Z","abstract_excerpt":"Sign language translation (SLT) converts continuous sign videos into spoken language text. Gloss-free approaches leverage pre-trained visual encoders and language models but rely on implicit cross-modal alignment from translation supervision alone. We present VTaMo, a framework that introduces explicit multi-granularity alignment at three levels: (1) local alignment via entropy-regularized optimal transport with a learnable null token for fine-grained frame-to-token correspondences; (2) global alignment via a learnable orthogonal transformation that calibrates embedding space geometry through "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.09126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T06:30:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d7ab3fc899f37d3f62d4069dd88b5be0f4dc50fc2ba972be75164b738fd85ea7","abstract_canon_sha256":"ce0fbd405467dd17941312c29d16aff7da71dd1204ef56dccedd72e67b00f1cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:18:44.573230Z","signature_b64":"Z7iIEr5oMDPNGlpb5+RAqp0smgDi+dXkpvCuhiqmjQ0GCa6O46lte+MuOqKdHA+BfMUolUa+njzFjZvPsulmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc5284a8c59d9412c9f7d5dbf8285d3e6867acbbb281e16be2741f5ee40247cb","last_reissued_at":"2026-07-13T01:18:44.571835Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:18:44.571835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VTaMo: Video-Text Alignment Model for Sign Language Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aoxiang Yang, Haomian Huang, Junyi Hu, Yi Fang, Zhewen He","submitted_at":"2026-07-10T06:30:50Z","abstract_excerpt":"Sign language translation (SLT) converts continuous sign videos into spoken language text. Gloss-free approaches leverage pre-trained visual encoders and language models but rely on implicit cross-modal alignment from translation supervision alone. We present VTaMo, a framework that introduces explicit multi-granularity alignment at three levels: (1) local alignment via entropy-regularized optimal transport with a learnable null token for fine-grained frame-to-token correspondences; (2) global alignment via a learnable orthogonal transformation that calibrates embedding space geometry through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09126","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.09126/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.09126","created_at":"2026-07-13T01:18:44.572548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09126v1","created_at":"2026-07-13T01:18:44.572548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09126","created_at":"2026-07-13T01:18:44.572548+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RJIJKGFTWKB","created_at":"2026-07-13T01:18:44.572548+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RJIJKGFTWKBFSPX","created_at":"2026-07-13T01:18:44.572548+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RJIJKGF","created_at":"2026-07-13T01:18:44.572548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ","json":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ.json","graph_json":"https://pith.science/api/pith-number/7RJIJKGFTWKBFSPX2XN7QKC5HZ/graph.json","events_json":"https://pith.science/api/pith-number/7RJIJKGFTWKBFSPX2XN7QKC5HZ/events.json","paper":"https://pith.science/paper/7RJIJKGF"},"agent_actions":{"view_html":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ","download_json":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ.json","view_paper":"https://pith.science/paper/7RJIJKGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09126&json=true","fetch_graph":"https://pith.science/api/pith-number/7RJIJKGFTWKBFSPX2XN7QKC5HZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7RJIJKGFTWKBFSPX2XN7QKC5HZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ/action/storage_attestation","attest_author":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ/action/author_attestation","sign_citation":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ/action/citation_signature","submit_replication":"https://pith.science/pith/7RJIJKGFTWKBFSPX2XN7QKC5HZ/action/replication_record"}},"created_at":"2026-07-13T01:18:44.572548+00:00","updated_at":"2026-07-13T01:18:44.572548+00:00"}