{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RRIZMZ4F4NAYBKYEU5GAVX7JQI","short_pith_number":"pith:RRIZMZ4F","schema_version":"1.0","canonical_sha256":"8c51966785e34180ab04a74c0adfe98216fc2931acd572a32a668da14235051a","source":{"kind":"arxiv","id":"2311.15954","version":1},"attestation_state":"computed","paper":{"title":"A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Beining Xu, Hexin Liu, Leibny Paola Garcia, Shuyue Stella Li, Wenhan Chao, Xiangyu Zhang","submitted_at":"2023-11-27T15:58:28Z","abstract_excerpt":"In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as a downstream task, we analyze the effect of model size, training objectives, and model architecture on the models' performance as a feature extractor for a set of topologically diverse corpora. We develop a novel metric, the Phonetic-Syntax Ratio (PSR), to measure the phonetic and synthetic information in the extracted representations using deep generalized"},"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":"2311.15954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T15:58:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2f64d44013af9e516fdebdfcc0daaab397301d2dd1266d44ce33032d427b76e9","abstract_canon_sha256":"ade7396c188327f67266beec9119dbee3aabec99c613d108ca16547a4a337a02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:11.667278Z","signature_b64":"0QMeQA6+zlrEia/tHABBUnkqpOzLkkLu/W8UoL0wepzIY3v4iOwzlULT11lYH1HI6EdfCgYj39kmtDGCL1XZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c51966785e34180ab04a74c0adfe98216fc2931acd572a32a668da14235051a","last_reissued_at":"2026-07-05T07:17:11.666877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:11.666877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Beining Xu, Hexin Liu, Leibny Paola Garcia, Shuyue Stella Li, Wenhan Chao, Xiangyu Zhang","submitted_at":"2023-11-27T15:58:28Z","abstract_excerpt":"In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as a downstream task, we analyze the effect of model size, training objectives, and model architecture on the models' performance as a feature extractor for a set of topologically diverse corpora. We develop a novel metric, the Phonetic-Syntax Ratio (PSR), to measure the phonetic and synthetic information in the extracted representations using deep generalized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15954","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/2311.15954/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":"2311.15954","created_at":"2026-07-05T07:17:11.666937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15954v1","created_at":"2026-07-05T07:17:11.666937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15954","created_at":"2026-07-05T07:17:11.666937+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRIZMZ4F4NAY","created_at":"2026-07-05T07:17:11.666937+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRIZMZ4F4NAYBKYE","created_at":"2026-07-05T07:17:11.666937+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRIZMZ4F","created_at":"2026-07-05T07:17:11.666937+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/RRIZMZ4F4NAYBKYEU5GAVX7JQI","json":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI.json","graph_json":"https://pith.science/api/pith-number/RRIZMZ4F4NAYBKYEU5GAVX7JQI/graph.json","events_json":"https://pith.science/api/pith-number/RRIZMZ4F4NAYBKYEU5GAVX7JQI/events.json","paper":"https://pith.science/paper/RRIZMZ4F"},"agent_actions":{"view_html":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI","download_json":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI.json","view_paper":"https://pith.science/paper/RRIZMZ4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15954&json=true","fetch_graph":"https://pith.science/api/pith-number/RRIZMZ4F4NAYBKYEU5GAVX7JQI/graph.json","fetch_events":"https://pith.science/api/pith-number/RRIZMZ4F4NAYBKYEU5GAVX7JQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/action/storage_attestation","attest_author":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/action/author_attestation","sign_citation":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/action/citation_signature","submit_replication":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/action/replication_record"}},"created_at":"2026-07-05T07:17:11.666937+00:00","updated_at":"2026-07-05T07:17:11.666937+00:00"}