{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RRIZMZ4F4NAYBKYEU5GAVX7JQI","short_pith_number":"pith:RRIZMZ4F","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"},"canonical_sha256":"8c51966785e34180ab04a74c0adfe98216fc2931acd572a32a668da14235051a","source":{"kind":"arxiv","id":"2311.15954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15954","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15954v1","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15954","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"RRIZMZ4F4NAY","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"RRIZMZ4F4NAYBKYE","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"RRIZMZ4F","created_at":"2026-07-05T07:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RRIZMZ4F4NAYBKYEU5GAVX7JQI","target":"record","payload":{"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"},"canonical_sha256":"8c51966785e34180ab04a74c0adfe98216fc2931acd572a32a668da14235051a","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"},"source_kind":"arxiv","source_id":"2311.15954","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EqzFePPS7lS7mS9S3XA5nalSE3iGZGh7Chj/Gk9edNi33jEeXHuHct9ZxnARfpTFc5jusabZ/Rkd/7P3jGTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:19.121311Z"},"content_sha256":"8a9a9b361497a6d51fa42ea3d6960d58855375513a6a2f5310504d1e07ad89d9","schema_version":"1.0","event_id":"sha256:8a9a9b361497a6d51fa42ea3d6960d58855375513a6a2f5310504d1e07ad89d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RRIZMZ4F4NAYBKYEU5GAVX7JQI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f05yAklanUIj57/7+8hLX0jgegxe3nLnrTn/GirysjdNU8TxksKj6ORwB7XV4fiHDiw38p+CRVYHzDscVX43Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:19.122245Z"},"content_sha256":"f9fcd05dd58935f55e6c02e85a8ee29b7a317d56d6ccbe0a363ce29a1b3c9466","schema_version":"1.0","event_id":"sha256:f9fcd05dd58935f55e6c02e85a8ee29b7a317d56d6ccbe0a363ce29a1b3c9466"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/bundle.json","state_url":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T06:23:19Z","links":{"resolver":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI","bundle":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/bundle.json","state":"https://pith.science/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRIZMZ4F4NAYBKYEU5GAVX7JQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RRIZMZ4F4NAYBKYEU5GAVX7JQI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ade7396c188327f67266beec9119dbee3aabec99c613d108ca16547a4a337a02","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T15:58:28Z","title_canon_sha256":"2f64d44013af9e516fdebdfcc0daaab397301d2dd1266d44ce33032d427b76e9"},"schema_version":"1.0","source":{"id":"2311.15954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15954","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15954v1","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15954","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"RRIZMZ4F4NAY","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"RRIZMZ4F4NAYBKYE","created_at":"2026-07-05T07:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"RRIZMZ4F","created_at":"2026-07-05T07:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:f9fcd05dd58935f55e6c02e85a8ee29b7a317d56d6ccbe0a363ce29a1b3c9466","target":"graph","created_at":"2026-07-05T07:17:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.15954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Beining Xu, Hexin Liu, Leibny Paola Garcia, Shuyue Stella Li, Wenhan Chao, Xiangyu Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T15:58:28Z","title":"A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15954","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a9a9b361497a6d51fa42ea3d6960d58855375513a6a2f5310504d1e07ad89d9","target":"record","created_at":"2026-07-05T07:17:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ade7396c188327f67266beec9119dbee3aabec99c613d108ca16547a4a337a02","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T15:58:28Z","title_canon_sha256":"2f64d44013af9e516fdebdfcc0daaab397301d2dd1266d44ce33032d427b76e9"},"schema_version":"1.0","source":{"id":"2311.15954","kind":"arxiv","version":1}},"canonical_sha256":"8c51966785e34180ab04a74c0adfe98216fc2931acd572a32a668da14235051a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c51966785e34180ab04a74c0adfe98216fc2931acd572a32a668da14235051a","first_computed_at":"2026-07-05T07:17:11.666877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:11.666877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0QMeQA6+zlrEia/tHABBUnkqpOzLkkLu/W8UoL0wepzIY3v4iOwzlULT11lYH1HI6EdfCgYj39kmtDGCL1XZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:11.667278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a9a9b361497a6d51fa42ea3d6960d58855375513a6a2f5310504d1e07ad89d9","sha256:f9fcd05dd58935f55e6c02e85a8ee29b7a317d56d6ccbe0a363ce29a1b3c9466"],"state_sha256":"402609fb9dbbca9e43d737bd4c42e9d9a06f04d5070d332d44a89f6a31b2cb5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7XIFYVRxaSgX8YGUowc7qxRkw/kobJrvJgCf5/lHia9mYuZoQRqV1nmY2V6ZsDOwXq3DhJ53Cs8kqc60yaRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:23:19.128131Z","bundle_sha256":"5030ee3057888db9718162a71e55551a36cc9bfc138e11d20d83418be93b43d9"}}