{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4SQ3I2S55EIIDVPVCEXQNOH3GA","short_pith_number":"pith:4SQ3I2S5","canonical_record":{"source":{"id":"2208.12888","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T23:00:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"725c32a2cbc723de7ab9b3be2579d7e9a99721777a0ec3825f87f9b8c99708a3","abstract_canon_sha256":"8887a02b400b1633c09a65208ff78fad4f43ca95c53fc34037a1cf089c539947"},"schema_version":"1.0"},"canonical_sha256":"e4a1b46a5de91081d5f5112f06b8fb302f5f6480427d279b36e99f9348bd7356","source":{"kind":"arxiv","id":"2208.12888","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12888","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12888v1","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12888","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"4SQ3I2S55EII","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"4SQ3I2S55EIIDVPV","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"4SQ3I2S5","created_at":"2026-07-05T04:52:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4SQ3I2S55EIIDVPVCEXQNOH3GA","target":"record","payload":{"canonical_record":{"source":{"id":"2208.12888","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T23:00:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"725c32a2cbc723de7ab9b3be2579d7e9a99721777a0ec3825f87f9b8c99708a3","abstract_canon_sha256":"8887a02b400b1633c09a65208ff78fad4f43ca95c53fc34037a1cf089c539947"},"schema_version":"1.0"},"canonical_sha256":"e4a1b46a5de91081d5f5112f06b8fb302f5f6480427d279b36e99f9348bd7356","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:52:00.403477Z","signature_b64":"T+kV2wLO3MXKWzuAGP9bZ9IglMm2UTcrrFHYT0VQNYEUCc9kqrQH8LihaNB3pMIwaswvApcFPYIVhzPlXwk1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4a1b46a5de91081d5f5112f06b8fb302f5f6480427d279b36e99f9348bd7356","last_reissued_at":"2026-07-05T04:52:00.402998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:52:00.402998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.12888","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":"2026-07-05T04:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TjgIBI0o0OQB3psJnMKLa2KOXywBC/Xmwrdv817nRAdregdj1NJK4A5wPQewuOfb4UnJJ2RU10V92yfH4Zg8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:20:11.133616Z"},"content_sha256":"cf64b952b7b243f2596d1aa6fcdb87628a6fee6a6551b6121bdbcacf21076c62","schema_version":"1.0","event_id":"sha256:cf64b952b7b243f2596d1aa6fcdb87628a6fee6a6551b6121bdbcacf21076c62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4SQ3I2S55EIIDVPVCEXQNOH3GA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emily Prud'hommeaux, Justin Spence, Zoey Liu","submitted_at":"2022-08-26T23:00:49Z","abstract_excerpt":"Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This \"hold-speaker(s)-out\" data partitioning strategy, however, may not be ideal for data sets in which the number of speakers is very small. This study investigates ten different data split methods for five languages with minimal ASR training resources. We find that (1) model performance varies greatly depending on which speaker is selected for testing; (2) the average word error rate (WER) across all held-out speakers is co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12888","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/2208.12888/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":"2026-07-05T04:52:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JI/KQG+cLZVsPYvkNBK3kCtiAZhk/X2eeANhlBVY3kKCnV5oc1M2jtbA8BkJpqBY4CPsPAW0imCBMjD3J5D1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:20:11.133945Z"},"content_sha256":"415636b0430810e98a1a4b409fd65aa9eadcde50309b6a1591d101c2101e8555","schema_version":"1.0","event_id":"sha256:415636b0430810e98a1a4b409fd65aa9eadcde50309b6a1591d101c2101e8555"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA/bundle.json","state_url":"https://pith.science/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA/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":"2026-08-14T19:20:11Z","links":{"resolver":"https://pith.science/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA","bundle":"https://pith.science/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA/bundle.json","state":"https://pith.science/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SQ3I2S55EIIDVPVCEXQNOH3GA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4SQ3I2S55EIIDVPVCEXQNOH3GA","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":"8887a02b400b1633c09a65208ff78fad4f43ca95c53fc34037a1cf089c539947","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T23:00:49Z","title_canon_sha256":"725c32a2cbc723de7ab9b3be2579d7e9a99721777a0ec3825f87f9b8c99708a3"},"schema_version":"1.0","source":{"id":"2208.12888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12888","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12888v1","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12888","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"4SQ3I2S55EII","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"4SQ3I2S55EIIDVPV","created_at":"2026-07-05T04:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"4SQ3I2S5","created_at":"2026-07-05T04:52:00Z"}],"graph_snapshots":[{"event_id":"sha256:415636b0430810e98a1a4b409fd65aa9eadcde50309b6a1591d101c2101e8555","target":"graph","created_at":"2026-07-05T04:52:00Z","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/2208.12888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This \"hold-speaker(s)-out\" data partitioning strategy, however, may not be ideal for data sets in which the number of speakers is very small. This study investigates ten different data split methods for five languages with minimal ASR training resources. We find that (1) model performance varies greatly depending on which speaker is selected for testing; (2) the average word error rate (WER) across all held-out speakers is co","authors_text":"Emily Prud'hommeaux, Justin Spence, Zoey Liu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T23:00:49Z","title":"Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12888","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:cf64b952b7b243f2596d1aa6fcdb87628a6fee6a6551b6121bdbcacf21076c62","target":"record","created_at":"2026-07-05T04:52:00Z","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":"8887a02b400b1633c09a65208ff78fad4f43ca95c53fc34037a1cf089c539947","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-26T23:00:49Z","title_canon_sha256":"725c32a2cbc723de7ab9b3be2579d7e9a99721777a0ec3825f87f9b8c99708a3"},"schema_version":"1.0","source":{"id":"2208.12888","kind":"arxiv","version":1}},"canonical_sha256":"e4a1b46a5de91081d5f5112f06b8fb302f5f6480427d279b36e99f9348bd7356","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4a1b46a5de91081d5f5112f06b8fb302f5f6480427d279b36e99f9348bd7356","first_computed_at":"2026-07-05T04:52:00.402998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:52:00.402998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T+kV2wLO3MXKWzuAGP9bZ9IglMm2UTcrrFHYT0VQNYEUCc9kqrQH8LihaNB3pMIwaswvApcFPYIVhzPlXwk1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:52:00.403477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf64b952b7b243f2596d1aa6fcdb87628a6fee6a6551b6121bdbcacf21076c62","sha256:415636b0430810e98a1a4b409fd65aa9eadcde50309b6a1591d101c2101e8555"],"state_sha256":"9254bbeea31e801124bd3068455ae4bd12e71918e5d1ce497c1f124f3e90add4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQpNrs8v+hxqRJbBAVXmgLndRiSKylnyRmVgqIak8Z+uVi/Ujc0x4uCVYbYdnIWwhysdftS6qkc2f0X/Bew6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:20:11.137348Z","bundle_sha256":"87ca1e209c63406d42604e4cbb6b9acd3e2cd480f467f0fd942964a4a8c61db9"}}