{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JUESROYYQ7T4IUSZUWHMPB2IIE","short_pith_number":"pith:JUESROYY","canonical_record":{"source":{"id":"2504.07024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T16:38:45Z","cross_cats_sorted":[],"title_canon_sha256":"4e643019648dfdaa01611a27dc560f8e5ac1974e22ad07f37c43514d733eafa8","abstract_canon_sha256":"04702f15e728c9fc46d48fa6ce7ef9545d8a29e9be59c0118692c16420f3ac3c"},"schema_version":"1.0"},"canonical_sha256":"4d0928bb1887e7c45259a58ec787484125c5a577b0ee71b26514f052f29d9292","source":{"kind":"arxiv","id":"2504.07024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07024","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07024v1","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07024","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"JUESROYYQ7T4","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"JUESROYYQ7T4IUSZ","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"JUESROYY","created_at":"2026-07-05T10:46:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JUESROYYQ7T4IUSZUWHMPB2IIE","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T16:38:45Z","cross_cats_sorted":[],"title_canon_sha256":"4e643019648dfdaa01611a27dc560f8e5ac1974e22ad07f37c43514d733eafa8","abstract_canon_sha256":"04702f15e728c9fc46d48fa6ce7ef9545d8a29e9be59c0118692c16420f3ac3c"},"schema_version":"1.0"},"canonical_sha256":"4d0928bb1887e7c45259a58ec787484125c5a577b0ee71b26514f052f29d9292","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:50.027697Z","signature_b64":"/Itx1svJlE2AAorhMLfYK1MB83YzmsNp6gnmwkIuF/Pn9X3oyfK8NRZlHlLO8EOqCv3DsRC84Q7s0+JphroTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d0928bb1887e7c45259a58ec787484125c5a577b0ee71b26514f052f29d9292","last_reissued_at":"2026-07-05T10:46:50.027201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:50.027201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07024","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":"2026-07-05T10:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gF9gT53EWs1g6FTSD8B6vtby+PdHX6uYPzfRE53tlOw+zhEPjrtRRcNE6j8OAFdwf1LpqmvN2X5LtcVDuHfcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:46:58.347979Z"},"content_sha256":"f8319bf008b962090a26a027a9a814ff74f7863316021fd7e69a268cf0e2b445","schema_version":"1.0","event_id":"sha256:f8319bf008b962090a26a027a9a814ff74f7863316021fd7e69a268cf0e2b445"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JUESROYYQ7T4IUSZUWHMPB2IIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Augmentation and Hyperparameter Tuning for Low-Resource MFA","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessio Tosolini, Claire Bowern","submitted_at":"2025-04-09T16:38:45Z","abstract_excerpt":"A continued issue for those working with computational tools and endangered and under-resourced languages is the lower accuracy of results for languages with smaller amounts of data. We attempt to ameliorate this issue by using data augmentation methods to increase corpus size, comparing augmentation to hyperparameter tuning for multilingual forced alignment. Unlike text augmentation methods, audio augmentation does not lead to substantially increased performance. Hyperparameter tuning, on the other hand, results in substantial improvement without (for this amount of data) infeasible additiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07024","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/2504.07024/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":"2026-07-05T10:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GP2mLu5xisxHTb4BF2zeddWLWxyeQb9259tyoxjmPv2FNMeO8G8zpiSyhMb5gfhv03fbtF9hg5mnf7RmwBPuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:46:58.348530Z"},"content_sha256":"2196f5ff1d81d2335df18801eb63023a9f62cef5f3755e0dff89c6c316d9e8eb","schema_version":"1.0","event_id":"sha256:2196f5ff1d81d2335df18801eb63023a9f62cef5f3755e0dff89c6c316d9e8eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUESROYYQ7T4IUSZUWHMPB2IIE/bundle.json","state_url":"https://pith.science/pith/JUESROYYQ7T4IUSZUWHMPB2IIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUESROYYQ7T4IUSZUWHMPB2IIE/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":"2026-08-08T12:46:58Z","links":{"resolver":"https://pith.science/pith/JUESROYYQ7T4IUSZUWHMPB2IIE","bundle":"https://pith.science/pith/JUESROYYQ7T4IUSZUWHMPB2IIE/bundle.json","state":"https://pith.science/pith/JUESROYYQ7T4IUSZUWHMPB2IIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUESROYYQ7T4IUSZUWHMPB2IIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JUESROYYQ7T4IUSZUWHMPB2IIE","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":"04702f15e728c9fc46d48fa6ce7ef9545d8a29e9be59c0118692c16420f3ac3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T16:38:45Z","title_canon_sha256":"4e643019648dfdaa01611a27dc560f8e5ac1974e22ad07f37c43514d733eafa8"},"schema_version":"1.0","source":{"id":"2504.07024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07024","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07024v1","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07024","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"JUESROYYQ7T4","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"JUESROYYQ7T4IUSZ","created_at":"2026-07-05T10:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"JUESROYY","created_at":"2026-07-05T10:46:50Z"}],"graph_snapshots":[{"event_id":"sha256:2196f5ff1d81d2335df18801eb63023a9f62cef5f3755e0dff89c6c316d9e8eb","target":"graph","created_at":"2026-07-05T10:46:50Z","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/2504.07024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A continued issue for those working with computational tools and endangered and under-resourced languages is the lower accuracy of results for languages with smaller amounts of data. We attempt to ameliorate this issue by using data augmentation methods to increase corpus size, comparing augmentation to hyperparameter tuning for multilingual forced alignment. Unlike text augmentation methods, audio augmentation does not lead to substantially increased performance. Hyperparameter tuning, on the other hand, results in substantial improvement without (for this amount of data) infeasible additiona","authors_text":"Alessio Tosolini, Claire Bowern","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T16:38:45Z","title":"Data Augmentation and Hyperparameter Tuning for Low-Resource MFA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07024","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:f8319bf008b962090a26a027a9a814ff74f7863316021fd7e69a268cf0e2b445","target":"record","created_at":"2026-07-05T10:46:50Z","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":"04702f15e728c9fc46d48fa6ce7ef9545d8a29e9be59c0118692c16420f3ac3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T16:38:45Z","title_canon_sha256":"4e643019648dfdaa01611a27dc560f8e5ac1974e22ad07f37c43514d733eafa8"},"schema_version":"1.0","source":{"id":"2504.07024","kind":"arxiv","version":1}},"canonical_sha256":"4d0928bb1887e7c45259a58ec787484125c5a577b0ee71b26514f052f29d9292","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d0928bb1887e7c45259a58ec787484125c5a577b0ee71b26514f052f29d9292","first_computed_at":"2026-07-05T10:46:50.027201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:50.027201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Itx1svJlE2AAorhMLfYK1MB83YzmsNp6gnmwkIuF/Pn9X3oyfK8NRZlHlLO8EOqCv3DsRC84Q7s0+JphroTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:50.027697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8319bf008b962090a26a027a9a814ff74f7863316021fd7e69a268cf0e2b445","sha256:2196f5ff1d81d2335df18801eb63023a9f62cef5f3755e0dff89c6c316d9e8eb"],"state_sha256":"0b7e3d12254bce9e1f5b9c7a157b92bb09549f1e22889b6ff48a9a549cf6ec27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"19js+L23H4/ROIC8j3CovuZ8/W3+aW1TW8WmNcuUDY1Ggv6yQ+dKtYScLVGhXuOrY1mqLv5BwtKYZXjd4wZcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:46:58.353370Z","bundle_sha256":"47ccbf3dac288b5a5db3bced326d60f161ad9f2232297116f683ee2a1bf12d0b"}}