{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7RJIJKGFTWKBFSPX2XN7QKC5HZ","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":"ce0fbd405467dd17941312c29d16aff7da71dd1204ef56dccedd72e67b00f1cf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T06:30:50Z","title_canon_sha256":"d7ab3fc899f37d3f62d4069dd88b5be0f4dc50fc2ba972be75164b738fd85ea7"},"schema_version":"1.0","source":{"id":"2607.09126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09126","created_at":"2026-07-13T01:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09126v1","created_at":"2026-07-13T01:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09126","created_at":"2026-07-13T01:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"7RJIJKGFTWKB","created_at":"2026-07-13T01:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"7RJIJKGFTWKBFSPX","created_at":"2026-07-13T01:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"7RJIJKGF","created_at":"2026-07-13T01:18:44Z"}],"graph_snapshots":[{"event_id":"sha256:bdd0b5f599995b5c921b08542a9f1895f3aeb58ddc7bd3157bbe1df3c9ae6449","target":"graph","created_at":"2026-07-13T01:18:44Z","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/2607.09126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aoxiang Yang, Haomian Huang, Junyi Hu, Yi Fang, Zhewen He","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T06:30:50Z","title":"VTaMo: Video-Text Alignment Model for Sign Language Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09126","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:fd2a1c69460039fbf2b15032fe48be5a4e10f1a017334668359cf51ef9a73bdf","target":"record","created_at":"2026-07-13T01:18:44Z","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":"ce0fbd405467dd17941312c29d16aff7da71dd1204ef56dccedd72e67b00f1cf","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T06:30:50Z","title_canon_sha256":"d7ab3fc899f37d3f62d4069dd88b5be0f4dc50fc2ba972be75164b738fd85ea7"},"schema_version":"1.0","source":{"id":"2607.09126","kind":"arxiv","version":1}},"canonical_sha256":"fc5284a8c59d9412c9f7d5dbf8285d3e6867acbbb281e16be2741f5ee40247cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc5284a8c59d9412c9f7d5dbf8285d3e6867acbbb281e16be2741f5ee40247cb","first_computed_at":"2026-07-13T01:18:44.571835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:18:44.571835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z7iIEr5oMDPNGlpb5+RAqp0smgDi+dXkpvCuhiqmjQ0GCa6O46lte+MuOqKdHA+BfMUolUa+njzFjZvPsulmAQ==","signature_status":"signed_v1","signed_at":"2026-07-13T01:18:44.573230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd2a1c69460039fbf2b15032fe48be5a4e10f1a017334668359cf51ef9a73bdf","sha256:bdd0b5f599995b5c921b08542a9f1895f3aeb58ddc7bd3157bbe1df3c9ae6449"],"state_sha256":"5cabb20731dea180abc49ee787d61e4d768d0d3f23a666b817cf937a68bd4647"}