{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XRJIYVZ4FJKRTB5ARBMWHDOC2T","short_pith_number":"pith:XRJIYVZ4","schema_version":"1.0","canonical_sha256":"bc528c573c2a551987a08859638dc2d4d7e4af2c5764bf716e19874fb90e1570","source":{"kind":"arxiv","id":"2505.20066","version":1},"attestation_state":"computed","paper":{"title":"Automated data curation for self-supervised learning in underwater acoustic analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Burooj Ghani, Hilde I Hummel, Rob van der Mei, Sandjai Bhulai","submitted_at":"2025-05-26T14:50:04Z","abstract_excerpt":"The sustainability of the ocean ecosystem is threatened by increased levels of sound pollution, making monitoring crucial to understand its variability and impact. Passive acoustic monitoring (PAM) systems collect a large amount of underwater sound recordings, but the large volume of data makes manual analysis impossible, creating the need for automation. Although machine learning offers a potential solution, most underwater acoustic recordings are unlabeled. Self-supervised learning models have demonstrated success in learning from large-scale unlabeled data in various domains like computer v"},"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":"2505.20066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-26T14:50:04Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"908c1d7c001565ab790e4a9a2cd6247daf10a7dd87aec3d2de188bacf0234240","abstract_canon_sha256":"12e59f88efba1a87f75237cc69826f9082ebd71a59db3a60b11fe92f67d6413f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:52.111827Z","signature_b64":"lPwk1IUrsag/TAn7UfWYcb1DY8XXrg2SNwtBXunhZCmOK8lB9wqBmOMnKK+gnSSFYyMIpGp6e7GuXR4qOrf4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc528c573c2a551987a08859638dc2d4d7e4af2c5764bf716e19874fb90e1570","last_reissued_at":"2026-07-05T11:09:52.111348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:52.111348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated data curation for self-supervised learning in underwater acoustic analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Burooj Ghani, Hilde I Hummel, Rob van der Mei, Sandjai Bhulai","submitted_at":"2025-05-26T14:50:04Z","abstract_excerpt":"The sustainability of the ocean ecosystem is threatened by increased levels of sound pollution, making monitoring crucial to understand its variability and impact. Passive acoustic monitoring (PAM) systems collect a large amount of underwater sound recordings, but the large volume of data makes manual analysis impossible, creating the need for automation. Although machine learning offers a potential solution, most underwater acoustic recordings are unlabeled. Self-supervised learning models have demonstrated success in learning from large-scale unlabeled data in various domains like computer v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20066","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/2505.20066/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":"2505.20066","created_at":"2026-07-05T11:09:52.111407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20066v1","created_at":"2026-07-05T11:09:52.111407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20066","created_at":"2026-07-05T11:09:52.111407+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRJIYVZ4FJKR","created_at":"2026-07-05T11:09:52.111407+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRJIYVZ4FJKRTB5A","created_at":"2026-07-05T11:09:52.111407+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRJIYVZ4","created_at":"2026-07-05T11:09:52.111407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20066","citing_title":"Automated data curation for self-supervised learning in underwater acoustic analysis","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T","json":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T.json","graph_json":"https://pith.science/api/pith-number/XRJIYVZ4FJKRTB5ARBMWHDOC2T/graph.json","events_json":"https://pith.science/api/pith-number/XRJIYVZ4FJKRTB5ARBMWHDOC2T/events.json","paper":"https://pith.science/paper/XRJIYVZ4"},"agent_actions":{"view_html":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T","download_json":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T.json","view_paper":"https://pith.science/paper/XRJIYVZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20066&json=true","fetch_graph":"https://pith.science/api/pith-number/XRJIYVZ4FJKRTB5ARBMWHDOC2T/graph.json","fetch_events":"https://pith.science/api/pith-number/XRJIYVZ4FJKRTB5ARBMWHDOC2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T/action/storage_attestation","attest_author":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T/action/author_attestation","sign_citation":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T/action/citation_signature","submit_replication":"https://pith.science/pith/XRJIYVZ4FJKRTB5ARBMWHDOC2T/action/replication_record"}},"created_at":"2026-07-05T11:09:52.111407+00:00","updated_at":"2026-07-05T11:09:52.111407+00:00"}