{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BAN34OTTXK7AXJSKFNKQTJZLIS","short_pith_number":"pith:BAN34OTT","schema_version":"1.0","canonical_sha256":"081bbe3a73babe0ba64a2b5509a72b448f5660d6ea68815173bad0de44db7441","source":{"kind":"arxiv","id":"2408.08544","version":1},"attestation_state":"computed","paper":{"title":"Scaling up Multimodal Pre-training for Sign Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Houqiang Li, Weichao Zhao, Wengang Zhou, Zecheng Li","submitted_at":"2024-08-16T06:04:25Z","abstract_excerpt":"Sign language serves as the primary meaning of communication for the deaf-mute community. Different from spoken language, it commonly conveys information by the collaboration of manual features, i.e., hand gestures and body movements, and non-manual features, i.e., facial expressions and mouth cues. To facilitate communication between the deaf-mute and hearing people, a series of sign language understanding (SLU) tasks have been studied in recent years, including isolated/continuous sign language recognition (ISLR/CSLR), gloss-free sign language translation (GF-SLT) and sign language retrieval"},"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":"2408.08544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-16T06:04:25Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"537965a074e7c02dc00f8fd3b3d6877ab859cb32068bbbb3675a421c3d085e6a","abstract_canon_sha256":"20180f64d72ee389804e027a8fbf543e54efd3dd846255d48e935d1d0360c984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:56.563106Z","signature_b64":"cRkP1v8CfY8sQdtMJxj/y/THr6tc8pjbYO2L7P7WmC2tzZ9EubYQOOwOpvLA3Xj2O50lVH2TM/xc5Cl0lWMvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081bbe3a73babe0ba64a2b5509a72b448f5660d6ea68815173bad0de44db7441","last_reissued_at":"2026-07-05T08:55:56.562631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:56.562631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling up Multimodal Pre-training for Sign Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Houqiang Li, Weichao Zhao, Wengang Zhou, Zecheng Li","submitted_at":"2024-08-16T06:04:25Z","abstract_excerpt":"Sign language serves as the primary meaning of communication for the deaf-mute community. Different from spoken language, it commonly conveys information by the collaboration of manual features, i.e., hand gestures and body movements, and non-manual features, i.e., facial expressions and mouth cues. To facilitate communication between the deaf-mute and hearing people, a series of sign language understanding (SLU) tasks have been studied in recent years, including isolated/continuous sign language recognition (ISLR/CSLR), gloss-free sign language translation (GF-SLT) and sign language retrieval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08544","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/2408.08544/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":"2408.08544","created_at":"2026-07-05T08:55:56.562708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08544v1","created_at":"2026-07-05T08:55:56.562708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08544","created_at":"2026-07-05T08:55:56.562708+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAN34OTTXK7A","created_at":"2026-07-05T08:55:56.562708+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAN34OTTXK7AXJSK","created_at":"2026-07-05T08:55:56.562708+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAN34OTT","created_at":"2026-07-05T08:55:56.562708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11225","citing_title":"Sign Language Recognition in the Age of LLMs","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15301","citing_title":"Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS","json":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS.json","graph_json":"https://pith.science/api/pith-number/BAN34OTTXK7AXJSKFNKQTJZLIS/graph.json","events_json":"https://pith.science/api/pith-number/BAN34OTTXK7AXJSKFNKQTJZLIS/events.json","paper":"https://pith.science/paper/BAN34OTT"},"agent_actions":{"view_html":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS","download_json":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS.json","view_paper":"https://pith.science/paper/BAN34OTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08544&json=true","fetch_graph":"https://pith.science/api/pith-number/BAN34OTTXK7AXJSKFNKQTJZLIS/graph.json","fetch_events":"https://pith.science/api/pith-number/BAN34OTTXK7AXJSKFNKQTJZLIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS/action/storage_attestation","attest_author":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS/action/author_attestation","sign_citation":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS/action/citation_signature","submit_replication":"https://pith.science/pith/BAN34OTTXK7AXJSKFNKQTJZLIS/action/replication_record"}},"created_at":"2026-07-05T08:55:56.562708+00:00","updated_at":"2026-07-05T08:55:56.562708+00:00"}