{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AZHKINFPHIY7IPMDFIHJR6U2SW","short_pith_number":"pith:AZHKINFP","schema_version":"1.0","canonical_sha256":"064ea434af3a31f43d832a0e98fa9a95b2c8807db643d3129058d15cd19f37f2","source":{"kind":"arxiv","id":"2407.12842","version":1},"attestation_state":"computed","paper":{"title":"MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feng Zheng, Jian Ma, Wenguan Wang, Yi Yang","submitted_at":"2024-07-04T13:53:50Z","abstract_excerpt":"Sign language understanding has made significant strides; however, there is still no viable solution for generating sign sequences directly from entire spoken content, e.g., text or speech. In this paper, we propose a unified framework for continuous sign language production, easing communication between sign and non-sign language users. In particular, a sequence diffusion model, utilizing embeddings extracted from text or speech, is crafted to generate sign predictions step by step. Moreover, by creating a joint embedding space for text, audio, and sign, we bind these modalities and leverage "},"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":"2407.12842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T13:53:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b05f8c29a71cfbcd346c10c1cf345d655f5bd5f95206eb18e2ba0bb2d74a392b","abstract_canon_sha256":"9996c9e9bb2b147dc5238813eed77f3ed7d1a7f41af57de6d1b4fbceec8fa689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:12.441976Z","signature_b64":"FvJBGQqg42kEt3nmUWb9C8zPuRXOqOIoiseyFgwHEpdsQSn29FEYUvoQ8fHA4OWGdoyNwuaNHRvw7wF9s7mQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"064ea434af3a31f43d832a0e98fa9a95b2c8807db643d3129058d15cd19f37f2","last_reissued_at":"2026-07-05T08:45:12.441556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:12.441556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feng Zheng, Jian Ma, Wenguan Wang, Yi Yang","submitted_at":"2024-07-04T13:53:50Z","abstract_excerpt":"Sign language understanding has made significant strides; however, there is still no viable solution for generating sign sequences directly from entire spoken content, e.g., text or speech. In this paper, we propose a unified framework for continuous sign language production, easing communication between sign and non-sign language users. In particular, a sequence diffusion model, utilizing embeddings extracted from text or speech, is crafted to generate sign predictions step by step. Moreover, by creating a joint embedding space for text, audio, and sign, we bind these modalities and leverage "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12842","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/2407.12842/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":"2407.12842","created_at":"2026-07-05T08:45:12.441612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12842v1","created_at":"2026-07-05T08:45:12.441612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12842","created_at":"2026-07-05T08:45:12.441612+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZHKINFPHIY7","created_at":"2026-07-05T08:45:12.441612+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZHKINFPHIY7IPMD","created_at":"2026-07-05T08:45:12.441612+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZHKINFP","created_at":"2026-07-05T08:45:12.441612+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/AZHKINFPHIY7IPMDFIHJR6U2SW","json":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW.json","graph_json":"https://pith.science/api/pith-number/AZHKINFPHIY7IPMDFIHJR6U2SW/graph.json","events_json":"https://pith.science/api/pith-number/AZHKINFPHIY7IPMDFIHJR6U2SW/events.json","paper":"https://pith.science/paper/AZHKINFP"},"agent_actions":{"view_html":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW","download_json":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW.json","view_paper":"https://pith.science/paper/AZHKINFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12842&json=true","fetch_graph":"https://pith.science/api/pith-number/AZHKINFPHIY7IPMDFIHJR6U2SW/graph.json","fetch_events":"https://pith.science/api/pith-number/AZHKINFPHIY7IPMDFIHJR6U2SW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW/action/storage_attestation","attest_author":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW/action/author_attestation","sign_citation":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW/action/citation_signature","submit_replication":"https://pith.science/pith/AZHKINFPHIY7IPMDFIHJR6U2SW/action/replication_record"}},"created_at":"2026-07-05T08:45:12.441612+00:00","updated_at":"2026-07-05T08:45:12.441612+00:00"}