{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UTXXCNLURBDF2O6VPW5IDXIU6D","short_pith_number":"pith:UTXXCNLU","schema_version":"1.0","canonical_sha256":"a4ef71357488465d3bd57dba81dd14f0eda88b19b4064f15c0eca9f7021d2356","source":{"kind":"arxiv","id":"2503.15914","version":1},"attestation_state":"computed","paper":{"title":"Text-Driven Diffusion Model for Sign Language Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi He, Lechao Cheng, Ruobei Zhang, Shengeng Tang, Xu Wang, Yaxiong Wang","submitted_at":"2025-03-20T07:45:27Z","abstract_excerpt":"We introduce the hfut-lmc team's solution to the SLRTP Sign Production Challenge. The challenge aims to generate semantically aligned sign language pose sequences from text inputs. To this end, we propose a Text-driven Diffusion Model (TDM) framework. During the training phase, TDM utilizes an encoder to encode text sequences and incorporates them into the diffusion model as conditional input to generate sign pose sequences. To guarantee the high quality and accuracy of the generated pose sequences, we utilize two key loss functions. The joint loss function L_{joint} is used to precisely measu"},"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":"2503.15914","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T07:45:27Z","cross_cats_sorted":[],"title_canon_sha256":"d813fd4ff88e948f8dbf14b5e22a634e76fa3a696fe4ac0414e950c12f4b719b","abstract_canon_sha256":"d2aea5fcd7a2a2338c09b228dd277515cbc2f5335cc6f554b881c2568621b04c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:01.622754Z","signature_b64":"y1ozZHaGWyejyiKDgTZdtXH9Edf74VhZv7huXrFOavZooD4V+Ja72Tr0jyeea1ZpDhfO7u3cAPGNVsfRCT8sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4ef71357488465d3bd57dba81dd14f0eda88b19b4064f15c0eca9f7021d2356","last_reissued_at":"2026-07-05T10:36:01.622240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:01.622240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Driven Diffusion Model for Sign Language Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayi He, Lechao Cheng, Ruobei Zhang, Shengeng Tang, Xu Wang, Yaxiong Wang","submitted_at":"2025-03-20T07:45:27Z","abstract_excerpt":"We introduce the hfut-lmc team's solution to the SLRTP Sign Production Challenge. The challenge aims to generate semantically aligned sign language pose sequences from text inputs. To this end, we propose a Text-driven Diffusion Model (TDM) framework. During the training phase, TDM utilizes an encoder to encode text sequences and incorporates them into the diffusion model as conditional input to generate sign pose sequences. To guarantee the high quality and accuracy of the generated pose sequences, we utilize two key loss functions. The joint loss function L_{joint} is used to precisely measu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15914","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/2503.15914/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":"2503.15914","created_at":"2026-07-05T10:36:01.622297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15914v1","created_at":"2026-07-05T10:36:01.622297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15914","created_at":"2026-07-05T10:36:01.622297+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTXXCNLURBDF","created_at":"2026-07-05T10:36:01.622297+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTXXCNLURBDF2O6V","created_at":"2026-07-05T10:36:01.622297+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTXXCNLU","created_at":"2026-07-05T10:36:01.622297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22959","citing_title":"The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D","json":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D.json","graph_json":"https://pith.science/api/pith-number/UTXXCNLURBDF2O6VPW5IDXIU6D/graph.json","events_json":"https://pith.science/api/pith-number/UTXXCNLURBDF2O6VPW5IDXIU6D/events.json","paper":"https://pith.science/paper/UTXXCNLU"},"agent_actions":{"view_html":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D","download_json":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D.json","view_paper":"https://pith.science/paper/UTXXCNLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15914&json=true","fetch_graph":"https://pith.science/api/pith-number/UTXXCNLURBDF2O6VPW5IDXIU6D/graph.json","fetch_events":"https://pith.science/api/pith-number/UTXXCNLURBDF2O6VPW5IDXIU6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D/action/storage_attestation","attest_author":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D/action/author_attestation","sign_citation":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D/action/citation_signature","submit_replication":"https://pith.science/pith/UTXXCNLURBDF2O6VPW5IDXIU6D/action/replication_record"}},"created_at":"2026-07-05T10:36:01.622297+00:00","updated_at":"2026-07-05T10:36:01.622297+00:00"}