{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C4TDXTTRV5AGY4RLCCAD6IEJ2A","short_pith_number":"pith:C4TDXTTR","schema_version":"1.0","canonical_sha256":"17263bce71af406c722b10803f2089d01b4b12ccbcbcf63c06427bcd25d9d1ea","source":{"kind":"arxiv","id":"2108.07787","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Multi-scale Convolution for Dialect Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Song, Dawei Zhang, Huiyu Shi, Jinwen Huang, Shouyi Yin, Tianlong Kong, Wang Geng, Xiaorui Wang, Xin Wang","submitted_at":"2021-08-02T03:37:15Z","abstract_excerpt":"Time Delay Neural Networks (TDNN)-based methods are widely used in dialect identification. However, in previous work with TDNN application, subtle variant is being neglected in different feature scales. To address this issue, we propose a new architecture, named dynamic multi-scale convolution, which consists of dynamic kernel convolution, local multi-scale learning, and global multi-scale pooling. Dynamic kernel convolution captures features between short-term and long-term context adaptively. Local multi-scale learning, which represents multi-scale features at a granular level, is able to in"},"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":"2108.07787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T03:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"b4c6c02ebbb11463185ce2ed2725e0890a3bf39767e94d43e11a65714ffb5c28","abstract_canon_sha256":"5ac380164d0c8e9b187d59a70f81a5c7f64a6cc4d9909e79ddac3b8d32814f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:42.774244Z","signature_b64":"5zNGcMmXBW1q36TK2g07kKZVlFKr6tTu/KA3HQmtRJPRXaRWKhtaSLMer9oVmOuqaa73x4w3xjmt1QwEYMNCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17263bce71af406c722b10803f2089d01b4b12ccbcbcf63c06427bcd25d9d1ea","last_reissued_at":"2026-07-05T03:06:42.773719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:42.773719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Multi-scale Convolution for Dialect Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Song, Dawei Zhang, Huiyu Shi, Jinwen Huang, Shouyi Yin, Tianlong Kong, Wang Geng, Xiaorui Wang, Xin Wang","submitted_at":"2021-08-02T03:37:15Z","abstract_excerpt":"Time Delay Neural Networks (TDNN)-based methods are widely used in dialect identification. However, in previous work with TDNN application, subtle variant is being neglected in different feature scales. To address this issue, we propose a new architecture, named dynamic multi-scale convolution, which consists of dynamic kernel convolution, local multi-scale learning, and global multi-scale pooling. Dynamic kernel convolution captures features between short-term and long-term context adaptively. Local multi-scale learning, which represents multi-scale features at a granular level, is able to in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07787","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/2108.07787/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":"2108.07787","created_at":"2026-07-05T03:06:42.773774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07787v1","created_at":"2026-07-05T03:06:42.773774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07787","created_at":"2026-07-05T03:06:42.773774+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4TDXTTRV5AG","created_at":"2026-07-05T03:06:42.773774+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4TDXTTRV5AGY4RL","created_at":"2026-07-05T03:06:42.773774+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4TDXTTR","created_at":"2026-07-05T03:06:42.773774+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/C4TDXTTRV5AGY4RLCCAD6IEJ2A","json":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A.json","graph_json":"https://pith.science/api/pith-number/C4TDXTTRV5AGY4RLCCAD6IEJ2A/graph.json","events_json":"https://pith.science/api/pith-number/C4TDXTTRV5AGY4RLCCAD6IEJ2A/events.json","paper":"https://pith.science/paper/C4TDXTTR"},"agent_actions":{"view_html":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A","download_json":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A.json","view_paper":"https://pith.science/paper/C4TDXTTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07787&json=true","fetch_graph":"https://pith.science/api/pith-number/C4TDXTTRV5AGY4RLCCAD6IEJ2A/graph.json","fetch_events":"https://pith.science/api/pith-number/C4TDXTTRV5AGY4RLCCAD6IEJ2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A/action/storage_attestation","attest_author":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A/action/author_attestation","sign_citation":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A/action/citation_signature","submit_replication":"https://pith.science/pith/C4TDXTTRV5AGY4RLCCAD6IEJ2A/action/replication_record"}},"created_at":"2026-07-05T03:06:42.773774+00:00","updated_at":"2026-07-05T03:06:42.773774+00:00"}