{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:L4INGSGLDROZXH52AT3R6623HW","short_pith_number":"pith:L4INGSGL","schema_version":"1.0","canonical_sha256":"5f10d348cb1c5d9b9fba04f71f7b5b3d94797450264e664ca096f4753562ad2f","source":{"kind":"arxiv","id":"2110.05877","version":1},"attestation_state":"computed","paper":{"title":"OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gokul NC, Mitesh Khapra, Pratyush Kumar, Prem Selvaraj","submitted_at":"2021-10-12T10:33:02Z","abstract_excerpt":"AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing signs as individual words or as complete sentences. We introduce OpenHands, a library where we take four key ideas from the NLP community for low-resource languages and apply them to sign languages for word-level recognition. First, we propose using pose extracted through pretrained models as the standard modality of data to reduce training time and enable efficient inference, and we release standardized pose datasets fo"},"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":"2110.05877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T10:33:02Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"55c1e8637d111f529bef46feaceac61cd6476623cd61e33acaa521a28fd7f791","abstract_canon_sha256":"d8214c4be0fe70947ef31e49fed33a14551df2a0a934ad3a9867f56460e95789"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:07.829109Z","signature_b64":"EKz+5HAKZEblehqSKTZl8TZHKLQL4PM2JdSOvcIm1WyTfATUWBuWW0sZscMAYZ0Kv/nyEt4ho1oO+wcYzLHVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f10d348cb1c5d9b9fba04f71f7b5b3d94797450264e664ca096f4753562ad2f","last_reissued_at":"2026-07-05T03:22:07.828592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:07.828592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Gokul NC, Mitesh Khapra, Pratyush Kumar, Prem Selvaraj","submitted_at":"2021-10-12T10:33:02Z","abstract_excerpt":"AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing signs as individual words or as complete sentences. We introduce OpenHands, a library where we take four key ideas from the NLP community for low-resource languages and apply them to sign languages for word-level recognition. First, we propose using pose extracted through pretrained models as the standard modality of data to reduce training time and enable efficient inference, and we release standardized pose datasets fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05877","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/2110.05877/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":"2110.05877","created_at":"2026-07-05T03:22:07.828651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05877v1","created_at":"2026-07-05T03:22:07.828651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05877","created_at":"2026-07-05T03:22:07.828651+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4INGSGLDROZ","created_at":"2026-07-05T03:22:07.828651+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4INGSGLDROZXH52","created_at":"2026-07-05T03:22:07.828651+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4INGSGL","created_at":"2026-07-05T03:22:07.828651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18725","citing_title":"Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions","ref_index":207,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW","json":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW.json","graph_json":"https://pith.science/api/pith-number/L4INGSGLDROZXH52AT3R6623HW/graph.json","events_json":"https://pith.science/api/pith-number/L4INGSGLDROZXH52AT3R6623HW/events.json","paper":"https://pith.science/paper/L4INGSGL"},"agent_actions":{"view_html":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW","download_json":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW.json","view_paper":"https://pith.science/paper/L4INGSGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05877&json=true","fetch_graph":"https://pith.science/api/pith-number/L4INGSGLDROZXH52AT3R6623HW/graph.json","fetch_events":"https://pith.science/api/pith-number/L4INGSGLDROZXH52AT3R6623HW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW/action/storage_attestation","attest_author":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW/action/author_attestation","sign_citation":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW/action/citation_signature","submit_replication":"https://pith.science/pith/L4INGSGLDROZXH52AT3R6623HW/action/replication_record"}},"created_at":"2026-07-05T03:22:07.828651+00:00","updated_at":"2026-07-05T03:22:07.828651+00:00"}