{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VQO4DAHK2IHF7TWGC7FWDTWSS6","short_pith_number":"pith:VQO4DAHK","canonical_record":{"source":{"id":"1807.03697","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:12:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6b387779f2b5b328b2bb29035e778a0a6bd51a779960556bec630e1f5feaf82d","abstract_canon_sha256":"853e84feb202d7629cb6174ddabd5f8862787f0ed429b58783e4c7e28503a7d1"},"schema_version":"1.0"},"canonical_sha256":"ac1dc180ead20e5fcec617cb61ced2978f8e1675c478d435bbda5375ee1b197a","source":{"kind":"arxiv","id":"1807.03697","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03697","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03697v2","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03697","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"VQO4DAHK2IHF","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VQO4DAHK2IHF7TWG","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VQO4DAHK","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VQO4DAHK2IHF7TWGC7FWDTWSS6","target":"record","payload":{"canonical_record":{"source":{"id":"1807.03697","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:12:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6b387779f2b5b328b2bb29035e778a0a6bd51a779960556bec630e1f5feaf82d","abstract_canon_sha256":"853e84feb202d7629cb6174ddabd5f8862787f0ed429b58783e4c7e28503a7d1"},"schema_version":"1.0"},"canonical_sha256":"ac1dc180ead20e5fcec617cb61ced2978f8e1675c478d435bbda5375ee1b197a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:59.116847Z","signature_b64":"5hA5LYb9D213jJTm2ki/oa4WvCN1ekk4Qz8IAcVO8vK9TvV0j7JYTgXRX8QwaViwio2iWoRl52EvObQfZtQjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac1dc180ead20e5fcec617cb61ced2978f8e1675c478d435bbda5375ee1b197a","last_reissued_at":"2026-05-18T00:10:59.116065Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:59.116065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.03697","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBF/vsOriU9ZPDht97VJ08JnmZY2fX4u15864qT68BPHtQ60uk9ZDWERZp/4WohtAAmi38VdislYaq5HbCizDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T00:18:30.211823Z"},"content_sha256":"610cec7d03b9550c71faebaefc0b21e2b8099f3066e1d97eb0a22e57b16268b1","schema_version":"1.0","event_id":"sha256:610cec7d03b9550c71faebaefc0b21e2b8099f3066e1d97eb0a22e57b16268b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VQO4DAHK2IHF7TWGC7FWDTWSS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning for Audio Transcription on Low-Resource Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Stowell, Veronica Morfi","submitted_at":"2018-07-10T15:12:23Z","abstract_excerpt":"In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03697","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvWJ3IsfA6qWl+EgUkH4v9b8hhUzmV/P0R5VfRMarS47nmIfRUVkERJm7nAnqsIW+HXUsXqZvqdxuj9sAmACAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T00:18:30.212167Z"},"content_sha256":"4d9fa8de1e710e5b3c2bb8d5dea870fbe68f5205d8529cfc4fdf754de9f6c368","schema_version":"1.0","event_id":"sha256:4d9fa8de1e710e5b3c2bb8d5dea870fbe68f5205d8529cfc4fdf754de9f6c368"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6/bundle.json","state_url":"https://pith.science/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6/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":"2026-06-26T00:18:30Z","links":{"resolver":"https://pith.science/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6","bundle":"https://pith.science/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6/bundle.json","state":"https://pith.science/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQO4DAHK2IHF7TWGC7FWDTWSS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VQO4DAHK2IHF7TWGC7FWDTWSS6","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":"853e84feb202d7629cb6174ddabd5f8862787f0ed429b58783e4c7e28503a7d1","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:12:23Z","title_canon_sha256":"6b387779f2b5b328b2bb29035e778a0a6bd51a779960556bec630e1f5feaf82d"},"schema_version":"1.0","source":{"id":"1807.03697","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03697","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03697v2","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03697","created_at":"2026-05-18T00:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"VQO4DAHK2IHF","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VQO4DAHK2IHF7TWG","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VQO4DAHK","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:4d9fa8de1e710e5b3c2bb8d5dea870fbe68f5205d8529cfc4fdf754de9f6c368","target":"graph","created_at":"2026-05-18T00:10:59Z","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"},"paper":{"abstract_excerpt":"In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training perf","authors_text":"Dan Stowell, Veronica Morfi","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:12:23Z","title":"Deep Learning for Audio Transcription on Low-Resource Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03697","kind":"arxiv","version":2},"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":"sha256:610cec7d03b9550c71faebaefc0b21e2b8099f3066e1d97eb0a22e57b16268b1","target":"record","created_at":"2026-05-18T00:10:59Z","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":"853e84feb202d7629cb6174ddabd5f8862787f0ed429b58783e4c7e28503a7d1","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:12:23Z","title_canon_sha256":"6b387779f2b5b328b2bb29035e778a0a6bd51a779960556bec630e1f5feaf82d"},"schema_version":"1.0","source":{"id":"1807.03697","kind":"arxiv","version":2}},"canonical_sha256":"ac1dc180ead20e5fcec617cb61ced2978f8e1675c478d435bbda5375ee1b197a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac1dc180ead20e5fcec617cb61ced2978f8e1675c478d435bbda5375ee1b197a","first_computed_at":"2026-05-18T00:10:59.116065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:59.116065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5hA5LYb9D213jJTm2ki/oa4WvCN1ekk4Qz8IAcVO8vK9TvV0j7JYTgXRX8QwaViwio2iWoRl52EvObQfZtQjAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:59.116847Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03697","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:610cec7d03b9550c71faebaefc0b21e2b8099f3066e1d97eb0a22e57b16268b1","sha256:4d9fa8de1e710e5b3c2bb8d5dea870fbe68f5205d8529cfc4fdf754de9f6c368"],"state_sha256":"2869035a86d57852f5cd93cef4a574eef411322ae3630d95b8e953b0d6e06afd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RExnENI41B6BBai5BairgLx+QcGbWihU98IaMpkXNVLaScaXAy7uU/YOnoFwBcqoXDApt2k28dpg8TQtqg7GAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T00:18:30.214102Z","bundle_sha256":"45d528e3927b8bfd68bf09693554bca6dd7077607dc90e68a158077f823baa52"}}