{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S7KIYSC4LK5AUAZG75OAD4OFS5","short_pith_number":"pith:S7KIYSC4","schema_version":"1.0","canonical_sha256":"97d48c485c5aba0a0326ff5c01f1c597401b7e6234c74890fede6f1597ebfb1b","source":{"kind":"arxiv","id":"2508.09372","version":1},"attestation_state":"computed","paper":{"title":"A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fakhri Karray, Md. Milon Islam, Md Rezwanul Haque, S M Taslim Uddin Raju","submitted_at":"2025-08-12T21:59:53Z","abstract_excerpt":"Continuous Sign Language Recognition (CSLR) faces multiple challenges, including significant inter-signer variability and poor generalization to novel sentence structures. Traditional solutions frequently fail to handle these issues efficiently. For overcoming these constraints, we propose a dual-architecture framework. For the Signer-Independent (SI) challenge, we propose a Signer-Invariant Conformer that combines convolutions with multi-head self-attention to learn robust, signer-agnostic representations from pose-based skeletal keypoints. For the Unseen-Sentences (US) task, we designed a Mu"},"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":"2508.09372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T21:59:53Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"5d3186404c7545c967afdd07766475c20c5aab351bfd1230e82f83a73a6c48bc","abstract_canon_sha256":"19e5d1ecfd398199571bd577821bd11c01c14dff01eb46c92fc4a1602063ddad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:13.599785Z","signature_b64":"dI5fg1jyuU9QoSqPlv/WQ4vh9K2HisKl+IZ/hF6MiLg//aQj7bvwGkFNjmodga0eyji77Km3sIxYcuQQ6XjpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d48c485c5aba0a0326ff5c01f1c597401b7e6234c74890fede6f1597ebfb1b","last_reissued_at":"2026-07-05T11:53:13.599299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:13.599299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fakhri Karray, Md. Milon Islam, Md Rezwanul Haque, S M Taslim Uddin Raju","submitted_at":"2025-08-12T21:59:53Z","abstract_excerpt":"Continuous Sign Language Recognition (CSLR) faces multiple challenges, including significant inter-signer variability and poor generalization to novel sentence structures. Traditional solutions frequently fail to handle these issues efficiently. For overcoming these constraints, we propose a dual-architecture framework. For the Signer-Independent (SI) challenge, we propose a Signer-Invariant Conformer that combines convolutions with multi-head self-attention to learn robust, signer-agnostic representations from pose-based skeletal keypoints. For the Unseen-Sentences (US) task, we designed a Mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09372","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/2508.09372/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":"2508.09372","created_at":"2026-07-05T11:53:13.599364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09372v1","created_at":"2026-07-05T11:53:13.599364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09372","created_at":"2026-07-05T11:53:13.599364+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7KIYSC4LK5A","created_at":"2026-07-05T11:53:13.599364+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7KIYSC4LK5AUAZG","created_at":"2026-07-05T11:53:13.599364+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7KIYSC4","created_at":"2026-07-05T11:53:13.599364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09356","citing_title":"Pseudo Empirical Likelihood Inference for Non-Probability Survey Samples","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5","json":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5.json","graph_json":"https://pith.science/api/pith-number/S7KIYSC4LK5AUAZG75OAD4OFS5/graph.json","events_json":"https://pith.science/api/pith-number/S7KIYSC4LK5AUAZG75OAD4OFS5/events.json","paper":"https://pith.science/paper/S7KIYSC4"},"agent_actions":{"view_html":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5","download_json":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5.json","view_paper":"https://pith.science/paper/S7KIYSC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09372&json=true","fetch_graph":"https://pith.science/api/pith-number/S7KIYSC4LK5AUAZG75OAD4OFS5/graph.json","fetch_events":"https://pith.science/api/pith-number/S7KIYSC4LK5AUAZG75OAD4OFS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5/action/storage_attestation","attest_author":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5/action/author_attestation","sign_citation":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5/action/citation_signature","submit_replication":"https://pith.science/pith/S7KIYSC4LK5AUAZG75OAD4OFS5/action/replication_record"}},"created_at":"2026-07-05T11:53:13.599364+00:00","updated_at":"2026-07-05T11:53:13.599364+00:00"}