{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GOH6NWQQVWVGFSTWC3R6YXOQO2","short_pith_number":"pith:GOH6NWQQ","schema_version":"1.0","canonical_sha256":"338fe6da10adaa62ca7616e3ec5dd0769b57b783eaf77a2e5db37833721bf67f","source":{"kind":"arxiv","id":"2105.11856","version":1},"attestation_state":"computed","paper":{"title":"Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Micha{\\l} Ko\\'smider","submitted_at":"2021-05-25T11:53:17Z","abstract_excerpt":"Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward method is introduced to address this problem. Two variants of the approach are presented. First requires aligned examples from multiple devices, the second approach alleviates this requirement. This method works for both time and frequency domain representations of audio recordings. Further, a relation to standardization and Cepstral Mean Subtraction is analysed"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2105.11856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-25T11:53:17Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2c4cb7687c678f65801d3b38bce95aeba6c2f559b58fb3b94a7126ca2bb303a1","abstract_canon_sha256":"a00d5db1a9f2242a056d75459357e2b2b97971643e7170cd81bf674a760bdc89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:57.431515Z","signature_b64":"9MUaxr/vuhzRh9CxuXtAkkzdCZEX4acTOlHqnUhHEOe4ZKNAYJNMAMh0v9BwxIArUoN4uIlxPm7mor8JhZacBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"338fe6da10adaa62ca7616e3ec5dd0769b57b783eaf77a2e5db37833721bf67f","last_reissued_at":"2026-07-05T02:42:57.431098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:57.431098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Micha{\\l} Ko\\'smider","submitted_at":"2021-05-25T11:53:17Z","abstract_excerpt":"Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward method is introduced to address this problem. Two variants of the approach are presented. First requires aligned examples from multiple devices, the second approach alleviates this requirement. This method works for both time and frequency domain representations of audio recordings. Further, a relation to standardization and Cepstral Mean Subtraction is analysed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11856","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/2105.11856/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2105.11856","created_at":"2026-07-05T02:42:57.431157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11856v1","created_at":"2026-07-05T02:42:57.431157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11856","created_at":"2026-07-05T02:42:57.431157+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOH6NWQQVWVG","created_at":"2026-07-05T02:42:57.431157+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOH6NWQQVWVGFSTW","created_at":"2026-07-05T02:42:57.431157+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOH6NWQQ","created_at":"2026-07-05T02:42:57.431157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13727","citing_title":"Adversarial Training Improves Generalization Under Distribution Shifts in Bioacoustics","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2","json":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2.json","graph_json":"https://pith.science/api/pith-number/GOH6NWQQVWVGFSTWC3R6YXOQO2/graph.json","events_json":"https://pith.science/api/pith-number/GOH6NWQQVWVGFSTWC3R6YXOQO2/events.json","paper":"https://pith.science/paper/GOH6NWQQ"},"agent_actions":{"view_html":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2","download_json":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2.json","view_paper":"https://pith.science/paper/GOH6NWQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11856&json=true","fetch_graph":"https://pith.science/api/pith-number/GOH6NWQQVWVGFSTWC3R6YXOQO2/graph.json","fetch_events":"https://pith.science/api/pith-number/GOH6NWQQVWVGFSTWC3R6YXOQO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2/action/storage_attestation","attest_author":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2/action/author_attestation","sign_citation":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2/action/citation_signature","submit_replication":"https://pith.science/pith/GOH6NWQQVWVGFSTWC3R6YXOQO2/action/replication_record"}},"created_at":"2026-07-05T02:42:57.431157+00:00","updated_at":"2026-07-05T02:42:57.431157+00:00"}