{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TOTP2MAW3DMHQUEUZUTB5CQIVL","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":"42dc3db315ac627d4cade94f7cc56df8742745e2d8f8a167717e51550d200d99","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T18:45:08Z","title_canon_sha256":"186c2adbbec291fd3e7dd526ac77c2403107e69e48aaa22b405bd270520fa84b"},"schema_version":"1.0","source":{"id":"2605.14031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14031","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14031v1","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14031","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"TOTP2MAW3DMH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TOTP2MAW3DMHQUEU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TOTP2MAW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9f551dad593d2c0a033ca4447753e6f5ead764b0e4d560d510c14d0517e9ec3f","target":"graph","created_at":"2026-05-17T23:39:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"In moderate-sized fine-grained bioacoustic settings, pretraining scale dominates objective design."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That performance differences observed on iNatSounds are driven primarily by pretraining data scale rather than uncontrolled factors such as exact model capacity, optimizer choices, or dataset-specific biases in the weakly labeled recordings."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"In moderate-sized fine-grained bioacoustics, pretraining scale of masked autoencoders on diverse general audio dominates over domain-specific objectives or data curation for transfer performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"For fine-grained bioacoustic classification with limited labels, pretraining on large general audio datasets beats additional domain-specific masked autoencoder training."}],"snapshot_sha256":"2225fd34e9f3c00c8a77410a9d91271017cb2305d8c5c51379bb6f33a3a79cac"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4b8110fc7eb73fa247e641717bf2b9d5bc25cb9443e54c9d15f662efc116a0c1"},"paper":{"abstract_excerpt":"Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are weakly annotated, often with only a single positive species label per recording, making supervised learning particularly challenging. Inspired by advances in computer vision, recent approaches have shifted toward self-supervised learning to capture the underlying structure of audio without relying on exhaustive annotations. In particular, masked autoencoders (MAE) have shown strong transferability on massive audio corp","authors_text":"Grant Van Horn, Mustafa Chasmai, Subhransu Maji, Wuao Liu","cross_cats":["cs.CV","cs.LG"],"headline":"For fine-grained bioacoustic classification with limited labels, pretraining on large general audio datasets beats additional domain-specific masked autoencoder training.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T18:45:08Z","title":"Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study"},"references":{"count":58,"internal_anchors":2,"resolved_work":58,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Mae-ast: Masked autoencoding audio spectrogram transformer","work_id":"0d9a5b49-c744-4674-b38c-2e06181f73dd","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Entropy-based analysis of influential factors for underwater acoustic target recognition in passive sonar data.Ocean Engineering, 342: 122908, 2025","work_id":"20e035c4-b9b4-4aa4-8370-2fde94c6de85","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"wav2vec 2.0: A framework for self-supervised learning of speech representations.Advances in neural infor- mation processing systems, 33:12449–12460, 2020","work_id":"163aa9cd-370e-46d2-8cfb-63f1a4398ac9","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Global biodiversity: indicators of recent declines","work_id":"a16884ff-e7e5-4560-b4d3-d4b9371a1c59","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"The inaturalist sounds dataset.Advances in Neural Information Processing Systems, 37:132524–132544,","work_id":"326b5f90-3748-45bd-bd24-ac7d5aecf34e","year":null}],"snapshot_sha256":"3134df022861d7102da2c65801d8f5b53e6b4e338c2412878bdf767d920672da"},"source":{"id":"2605.14031","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:41:23.006797Z","id":"46b520e4-8778-46cb-994b-52398184b698","model_set":{"reader":"grok-4.3"},"one_line_summary":"In moderate-sized fine-grained bioacoustics, pretraining scale of masked autoencoders on diverse general audio dominates over domain-specific objectives or data curation for transfer performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"For fine-grained bioacoustic classification with limited labels, pretraining on large general audio datasets beats additional domain-specific masked autoencoder training.","strongest_claim":"In moderate-sized fine-grained bioacoustic settings, pretraining scale dominates objective design.","weakest_assumption":"That performance differences observed on iNatSounds are driven primarily by pretraining data scale rather than uncontrolled factors such as exact model capacity, optimizer choices, or dataset-specific biases in the weakly labeled recordings."}},"verdict_id":"46b520e4-8778-46cb-994b-52398184b698"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:051ca77f58cf9b9e6aaa141b921045c875470c74fbef0bf5092983e866e31ece","target":"record","created_at":"2026-05-17T23:39:12Z","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":"42dc3db315ac627d4cade94f7cc56df8742745e2d8f8a167717e51550d200d99","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T18:45:08Z","title_canon_sha256":"186c2adbbec291fd3e7dd526ac77c2403107e69e48aaa22b405bd270520fa84b"},"schema_version":"1.0","source":{"id":"2605.14031","kind":"arxiv","version":1}},"canonical_sha256":"9ba6fd3016d8d8785094cd261e8a08aaed18d0ccac79abba5122a5f2cdf77b49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ba6fd3016d8d8785094cd261e8a08aaed18d0ccac79abba5122a5f2cdf77b49","first_computed_at":"2026-05-17T23:39:12.838495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:12.838495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Yp+Gv/yyJv4WFmcPtK+Tw/xBr52rGvLO2CYbcOIER7OM2vZ8O0GcmBvqjqQeVXLI0VX3QHuO4+RwBkeGV5HCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:12.838979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:051ca77f58cf9b9e6aaa141b921045c875470c74fbef0bf5092983e866e31ece","sha256:9f551dad593d2c0a033ca4447753e6f5ead764b0e4d560d510c14d0517e9ec3f"],"state_sha256":"3fe51d3a7ae4b4cfea20f2ec7e90812097122ea566de3a4d83030fd2198e80a8"}