{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7NTAAJT3DAHONTOE7AGZ6LEEOB","short_pith_number":"pith:7NTAAJT3","schema_version":"1.0","canonical_sha256":"fb6600267b180ee6cdc4f80d9f2c847078717774ebea970e952215e7ed30bc1d","source":{"kind":"arxiv","id":"2502.20838","version":3},"attestation_state":"computed","paper":{"title":"Weakly Supervised Detection and Temporal Localization of Whale Calls in Long-Duration Bioacoustic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin Yen, Kazuhiro Nakadai, Ragib Amin Nihal, Runwu Shi, Takeshi Ashizawa","submitted_at":"2025-02-28T08:34:12Z","abstract_excerpt":"Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls requires two separate annotation efforts: binary presence labels for classification and precise temporal boundaries for localization. A binary label for a multi-minute recording can be assigned in seconds, but timestamping every call within it requires hours of expert effort. Providing both is infeasible at operational scale. We present DSMIL-LocNet, a weakly supervised multiple instance learning (MIL) framework that performs both classification and tempor"},"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":"2502.20838","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-28T08:34:12Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"829d42099c4b44d0623aff11c1fefb02273bae4ee58f3b10c14e85660b313513","abstract_canon_sha256":"3c164d3c0db88a74c12d433a5db31d0291c5fa7bf04957b96d96bc0d8f266eb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:52.210471Z","signature_b64":"PVDcDkLRq14YZ1qgWrbiO/ky/AWDgIQeDM+7ZzvhPU6SlD1zDgyrFkzjqvrEPZJw77m0e1sTJazwuEMvqdqlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb6600267b180ee6cdc4f80d9f2c847078717774ebea970e952215e7ed30bc1d","last_reissued_at":"2026-05-29T01:04:52.210031Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:52.210031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly Supervised Detection and Temporal Localization of Whale Calls in Long-Duration Bioacoustic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin Yen, Kazuhiro Nakadai, Ragib Amin Nihal, Runwu Shi, Takeshi Ashizawa","submitted_at":"2025-02-28T08:34:12Z","abstract_excerpt":"Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls requires two separate annotation efforts: binary presence labels for classification and precise temporal boundaries for localization. A binary label for a multi-minute recording can be assigned in seconds, but timestamping every call within it requires hours of expert effort. Providing both is infeasible at operational scale. We present DSMIL-LocNet, a weakly supervised multiple instance learning (MIL) framework that performs both classification and tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20838","kind":"arxiv","version":3},"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/2502.20838/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":"2502.20838","created_at":"2026-05-29T01:04:52.210088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20838v3","created_at":"2026-05-29T01:04:52.210088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20838","created_at":"2026-05-29T01:04:52.210088+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NTAAJT3DAHO","created_at":"2026-05-29T01:04:52.210088+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NTAAJT3DAHONTOE","created_at":"2026-05-29T01:04:52.210088+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NTAAJT3","created_at":"2026-05-29T01:04:52.210088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.03914","citing_title":"Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB","json":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB.json","graph_json":"https://pith.science/api/pith-number/7NTAAJT3DAHONTOE7AGZ6LEEOB/graph.json","events_json":"https://pith.science/api/pith-number/7NTAAJT3DAHONTOE7AGZ6LEEOB/events.json","paper":"https://pith.science/paper/7NTAAJT3"},"agent_actions":{"view_html":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB","download_json":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB.json","view_paper":"https://pith.science/paper/7NTAAJT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20838&json=true","fetch_graph":"https://pith.science/api/pith-number/7NTAAJT3DAHONTOE7AGZ6LEEOB/graph.json","fetch_events":"https://pith.science/api/pith-number/7NTAAJT3DAHONTOE7AGZ6LEEOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB/action/storage_attestation","attest_author":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB/action/author_attestation","sign_citation":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB/action/citation_signature","submit_replication":"https://pith.science/pith/7NTAAJT3DAHONTOE7AGZ6LEEOB/action/replication_record"}},"created_at":"2026-05-29T01:04:52.210088+00:00","updated_at":"2026-05-29T01:04:52.210088+00:00"}