{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OTFMEZCUVU36KXIEQ2JFFMV2K4","short_pith_number":"pith:OTFMEZCU","canonical_record":{"source":{"id":"2210.14493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T05:38:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cbfa4df5edc7b7468ad95c309087ee51dac564c0407b3285d4888d6bb499784d","abstract_canon_sha256":"9828875234021591f4fd21068eb57b11a405974de9381dbed6578c1a066e4294"},"schema_version":"1.0"},"canonical_sha256":"74cac26454ad37e55d04869252b2ba573336c3189b0a25bb504bc73e9136ff9b","source":{"kind":"arxiv","id":"2210.14493","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14493","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14493v1","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14493","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"OTFMEZCUVU36","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"OTFMEZCUVU36KXIE","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"OTFMEZCU","created_at":"2026-07-05T05:10:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OTFMEZCUVU36KXIEQ2JFFMV2K4","target":"record","payload":{"canonical_record":{"source":{"id":"2210.14493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T05:38:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cbfa4df5edc7b7468ad95c309087ee51dac564c0407b3285d4888d6bb499784d","abstract_canon_sha256":"9828875234021591f4fd21068eb57b11a405974de9381dbed6578c1a066e4294"},"schema_version":"1.0"},"canonical_sha256":"74cac26454ad37e55d04869252b2ba573336c3189b0a25bb504bc73e9136ff9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:45.897464Z","signature_b64":"d1OWIMF9Kb/ww7iTCK5WvO5KI5uJXepuZFD7DBmRhOtR6KpK39br1U7IqSj5bBY9S53iFh9C8MU+zPlhroHLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74cac26454ad37e55d04869252b2ba573336c3189b0a25bb504bc73e9136ff9b","last_reissued_at":"2026-07-05T05:10:45.897001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:45.897001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.14493","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XlvKWwnYLhCeySzVFDny2qBCY3jEvWmJZUIruocnawqmxz2OpY12aU3j+O5khO1bub3UdWLOj4v7J+JD3oPXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:40:15.272614Z"},"content_sha256":"3c688e74cfefc2fd57e8c164405f70a1ecea5e90b4cc938f0d1417b4240460f0","schema_version":"1.0","event_id":"sha256:3c688e74cfefc2fd57e8c164405f70a1ecea5e90b4cc938f0d1417b4240460f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OTFMEZCUVU36KXIEQ2JFFMV2K4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AVES: Animal Vocalization Encoder based on Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Masato Hagiwara","submitted_at":"2022-10-26T05:38:50Z","abstract_excerpt":"The lack of annotated training data in bioacoustics hinders the use of large-scale neural network models trained in a supervised way. In order to leverage a large amount of unannotated audio data, we propose AVES (Animal Vocalization Encoder based on Self-Supervision), a self-supervised, transformer-based audio representation model for encoding animal vocalizations. We pretrain AVES on a diverse set of unannotated audio datasets and fine-tune them for downstream bioacoustics tasks. Comprehensive experiments with a suite of classification and detection tasks have shown that AVES outperforms all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14493","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/2210.14493/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3hNBiL48xSm6yVqm2N66LltUyuyiGpAB2/J2Zy1H0c6OYuEfQ7ViPEVDekdWqrQP4yDglCnl7McMVpjNunOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:40:15.273265Z"},"content_sha256":"0e221f7d2f83da1ce14b70314e0513fb5eb1addf73c337196954dc8d4c3aa2d3","schema_version":"1.0","event_id":"sha256:0e221f7d2f83da1ce14b70314e0513fb5eb1addf73c337196954dc8d4c3aa2d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4/bundle.json","state_url":"https://pith.science/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4/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":"2026-08-10T10:40:15Z","links":{"resolver":"https://pith.science/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4","bundle":"https://pith.science/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4/bundle.json","state":"https://pith.science/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTFMEZCUVU36KXIEQ2JFFMV2K4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OTFMEZCUVU36KXIEQ2JFFMV2K4","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":"9828875234021591f4fd21068eb57b11a405974de9381dbed6578c1a066e4294","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T05:38:50Z","title_canon_sha256":"cbfa4df5edc7b7468ad95c309087ee51dac564c0407b3285d4888d6bb499784d"},"schema_version":"1.0","source":{"id":"2210.14493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14493","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14493v1","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14493","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"OTFMEZCUVU36","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"OTFMEZCUVU36KXIE","created_at":"2026-07-05T05:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"OTFMEZCU","created_at":"2026-07-05T05:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:0e221f7d2f83da1ce14b70314e0513fb5eb1addf73c337196954dc8d4c3aa2d3","target":"graph","created_at":"2026-07-05T05:10:45Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.14493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The lack of annotated training data in bioacoustics hinders the use of large-scale neural network models trained in a supervised way. In order to leverage a large amount of unannotated audio data, we propose AVES (Animal Vocalization Encoder based on Self-Supervision), a self-supervised, transformer-based audio representation model for encoding animal vocalizations. We pretrain AVES on a diverse set of unannotated audio datasets and fine-tune them for downstream bioacoustics tasks. Comprehensive experiments with a suite of classification and detection tasks have shown that AVES outperforms all","authors_text":"Masato Hagiwara","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T05:38:50Z","title":"AVES: Animal Vocalization Encoder based on Self-Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14493","kind":"arxiv","version":1},"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":"sha256:3c688e74cfefc2fd57e8c164405f70a1ecea5e90b4cc938f0d1417b4240460f0","target":"record","created_at":"2026-07-05T05:10:45Z","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":"9828875234021591f4fd21068eb57b11a405974de9381dbed6578c1a066e4294","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-26T05:38:50Z","title_canon_sha256":"cbfa4df5edc7b7468ad95c309087ee51dac564c0407b3285d4888d6bb499784d"},"schema_version":"1.0","source":{"id":"2210.14493","kind":"arxiv","version":1}},"canonical_sha256":"74cac26454ad37e55d04869252b2ba573336c3189b0a25bb504bc73e9136ff9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74cac26454ad37e55d04869252b2ba573336c3189b0a25bb504bc73e9136ff9b","first_computed_at":"2026-07-05T05:10:45.897001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:45.897001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d1OWIMF9Kb/ww7iTCK5WvO5KI5uJXepuZFD7DBmRhOtR6KpK39br1U7IqSj5bBY9S53iFh9C8MU+zPlhroHLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:45.897464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c688e74cfefc2fd57e8c164405f70a1ecea5e90b4cc938f0d1417b4240460f0","sha256:0e221f7d2f83da1ce14b70314e0513fb5eb1addf73c337196954dc8d4c3aa2d3"],"state_sha256":"5f6cd01e719da96917be117008c35fdf30703da323ea3283c160f6151c04da95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfNcKy5zxXwplQ6FESJcU63pfScUSqjx+Qk1b/rpTxBJa3axvNT8EytG1REGGgzULoEenI4VBnQhT5d+gyzwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:40:15.278932Z","bundle_sha256":"94a7a3053515a406304d81d82e0e5d9896233f874b2da53f34687076f861cb96"}}