{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EYKAFT7V45DB4WV3L7MMQKNCLU","short_pith_number":"pith:EYKAFT7V","canonical_record":{"source":{"id":"2402.02302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9d4abcf8cdeb0e06d14de33d9e03c40f181f0c8d9ca3c2ade553fc0890f33121","abstract_canon_sha256":"b7aef93bfc2b03607e84904822787c571824b36358771fe93ce3d05198df233c"},"schema_version":"1.0"},"canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","source":{"kind":"arxiv","id":"2402.02302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02302","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02302v1","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02302","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"EYKAFT7V45DB","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"EYKAFT7V45DB4WV3","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"EYKAFT7V","created_at":"2026-07-05T07:41:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EYKAFT7V45DB4WV3L7MMQKNCLU","target":"record","payload":{"canonical_record":{"source":{"id":"2402.02302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9d4abcf8cdeb0e06d14de33d9e03c40f181f0c8d9ca3c2ade553fc0890f33121","abstract_canon_sha256":"b7aef93bfc2b03607e84904822787c571824b36358771fe93ce3d05198df233c"},"schema_version":"1.0"},"canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:13.182488Z","signature_b64":"VHBXymMyhcUjJkugGolEnv5Mpjda0HO7tush2zP3AVKjaV/tEcSr9IRuXP++MCVljAWTqypmdcN8/LnPKjB0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","last_reissued_at":"2026-07-05T07:41:13.182051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:13.182051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.02302","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":"2026-07-05T07:41:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3L7Tv5CBVr8GZMgsXeczxd2BdVldt/643Gft7MdSNsowvvtxBn60vXk+cRl7QOe5YX/vNgi0IoDGAjdmvTJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:58:16.030945Z"},"content_sha256":"2515e464c6f3fcb65d2c99dbde7d3ae82e704f57a2974c466752d5c0329fcf0d","schema_version":"1.0","event_id":"sha256:2515e464c6f3fcb65d2c99dbde7d3ae82e704f57a2974c466752d5c0329fcf0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EYKAFT7V45DB4WV3L7MMQKNCLU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Aryaman Arora, Dan Jurafsky, Georgios Paraskevopoulos, Nay San, Oliver Adams, Prabhjot Kaur, Xiluo He","submitted_at":"2024-02-03T23:54:03Z","abstract_excerpt":"While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the pre-training data. Continued pre-training on 70-200 hours of untranscribed speech in these languages can help -- but what about languages without that much recorded data? For such cases, we show that supplementing the target language with data from a similar, higher-resource 'donor' language can help. For example, continued pre-training on only 10 hours of low-re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02302","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/2402.02302/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":"2026-07-05T07:41:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWOxX+ZNAyMeXUyZO6332yrA+6mquDwqu8X/w8iy7xln6kWgXASg4hj2ehF0iv/SpETolTohZ0P6yorOcUfQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:58:16.031522Z"},"content_sha256":"4e8d090f78a62ddab8a31872b2bc537c9f6fbe531f079c8489d0cf0a755a10c7","schema_version":"1.0","event_id":"sha256:4e8d090f78a62ddab8a31872b2bc537c9f6fbe531f079c8489d0cf0a755a10c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EYKAFT7V45DB4WV3L7MMQKNCLU/bundle.json","state_url":"https://pith.science/pith/EYKAFT7V45DB4WV3L7MMQKNCLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EYKAFT7V45DB4WV3L7MMQKNCLU/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":"2026-08-08T06:58:16Z","links":{"resolver":"https://pith.science/pith/EYKAFT7V45DB4WV3L7MMQKNCLU","bundle":"https://pith.science/pith/EYKAFT7V45DB4WV3L7MMQKNCLU/bundle.json","state":"https://pith.science/pith/EYKAFT7V45DB4WV3L7MMQKNCLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EYKAFT7V45DB4WV3L7MMQKNCLU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EYKAFT7V45DB4WV3L7MMQKNCLU","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":"b7aef93bfc2b03607e84904822787c571824b36358771fe93ce3d05198df233c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","title_canon_sha256":"9d4abcf8cdeb0e06d14de33d9e03c40f181f0c8d9ca3c2ade553fc0890f33121"},"schema_version":"1.0","source":{"id":"2402.02302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02302","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02302v1","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02302","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"EYKAFT7V45DB","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"EYKAFT7V45DB4WV3","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"EYKAFT7V","created_at":"2026-07-05T07:41:13Z"}],"graph_snapshots":[{"event_id":"sha256:4e8d090f78a62ddab8a31872b2bc537c9f6fbe531f079c8489d0cf0a755a10c7","target":"graph","created_at":"2026-07-05T07:41:13Z","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/2402.02302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the pre-training data. Continued pre-training on 70-200 hours of untranscribed speech in these languages can help -- but what about languages without that much recorded data? For such cases, we show that supplementing the target language with data from a similar, higher-resource 'donor' language can help. For example, continued pre-training on only 10 hours of low-re","authors_text":"Aryaman Arora, Dan Jurafsky, Georgios Paraskevopoulos, Nay San, Oliver Adams, Prabhjot Kaur, Xiluo He","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","title":"Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02302","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":"sha256:2515e464c6f3fcb65d2c99dbde7d3ae82e704f57a2974c466752d5c0329fcf0d","target":"record","created_at":"2026-07-05T07:41:13Z","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":"b7aef93bfc2b03607e84904822787c571824b36358771fe93ce3d05198df233c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","title_canon_sha256":"9d4abcf8cdeb0e06d14de33d9e03c40f181f0c8d9ca3c2ade553fc0890f33121"},"schema_version":"1.0","source":{"id":"2402.02302","kind":"arxiv","version":1}},"canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","first_computed_at":"2026-07-05T07:41:13.182051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:13.182051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VHBXymMyhcUjJkugGolEnv5Mpjda0HO7tush2zP3AVKjaV/tEcSr9IRuXP++MCVljAWTqypmdcN8/LnPKjB0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:13.182488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2515e464c6f3fcb65d2c99dbde7d3ae82e704f57a2974c466752d5c0329fcf0d","sha256:4e8d090f78a62ddab8a31872b2bc537c9f6fbe531f079c8489d0cf0a755a10c7"],"state_sha256":"d934fa1ae6aa029b9980cd7385fec7e4d86c76dd893b0b09522b3b7c47752bbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LcH3D01OPaUF2WuC3yQlyZabTckfw8ZdpCv/qkL9K6hONTW7ocrCP7JaftWrpk6AI5LC0Z7txJhOcRCaWDrAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:58:16.036898Z","bundle_sha256":"08b2f95557284cfd1a4f5d19f4c7080b679d756695ba4687d5cf3a7f0ce4f0c0"}}