{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZIBAKLZIVREECTNRPD4ZH4VDZ7","short_pith_number":"pith:ZIBAKLZI","canonical_record":{"source":{"id":"2106.05408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-09T21:55:05Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"720551ee8a2c944ba144e442505458b598736b88ca96f68419f8631804f41b65","abstract_canon_sha256":"658e872ffe65c435c1c3442ab40e4f22b7b997ae56d5bac4f8ebc91c9deb64b9"},"schema_version":"1.0"},"canonical_sha256":"ca02052f28ac48414db178f993f2a3cffdd0960b10c6eda1ec2fa3d2b2b46d5e","source":{"kind":"arxiv","id":"2106.05408","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05408","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05408v1","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05408","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZIBAKLZIVREE","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZIBAKLZIVREECTNR","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZIBAKLZI","created_at":"2026-07-05T05:00:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZIBAKLZIVREECTNRPD4ZH4VDZ7","target":"record","payload":{"canonical_record":{"source":{"id":"2106.05408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-09T21:55:05Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"720551ee8a2c944ba144e442505458b598736b88ca96f68419f8631804f41b65","abstract_canon_sha256":"658e872ffe65c435c1c3442ab40e4f22b7b997ae56d5bac4f8ebc91c9deb64b9"},"schema_version":"1.0"},"canonical_sha256":"ca02052f28ac48414db178f993f2a3cffdd0960b10c6eda1ec2fa3d2b2b46d5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:37.245707Z","signature_b64":"JdlpsCfFf58GKLMBWRMy9X/fcunGDGDrWB0DUMKyK+SnQWAmaLgTfiUFYoN0PgZeFgnzrafeehlP7siN2gaBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca02052f28ac48414db178f993f2a3cffdd0960b10c6eda1ec2fa3d2b2b46d5e","last_reissued_at":"2026-07-05T05:00:37.245255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:37.245255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.05408","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":"2026-07-05T05:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQaJdanatOTIIkrNwtaXs8rfLOR56vsiSc26j9iJX4uwD/9QUSBP7pBLheZnFJsTup0sgSg60Bz13laR7XUWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:16:20.953294Z"},"content_sha256":"822a708858743a0544a677e9fb06b16b4569af3997d35a643a39c1f27d57b31e","schema_version":"1.0","event_id":"sha256:822a708858743a0544a677e9fb06b16b4569af3997d35a643a39c1f27d57b31e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZIBAKLZIVREECTNRPD4ZH4VDZ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audiovisual transfer learning for audio tagging and sound event detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Wim Boes","submitted_at":"2021-06-09T21:55:05Z","abstract_excerpt":"We study the merit of transfer learning for two sound recognition problems, i.e., audio tagging and sound event detection. Employing feature fusion, we adapt a baseline system utilizing only spectral acoustic inputs to also make use of pretrained auditory and visual features, extracted from networks built for different tasks and trained with external data. We perform experiments with these modified models on an audiovisual multi-label data set, of which the training partition contains a large number of unlabeled samples and a smaller amount of clips with weak annotations, indicating the clip-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05408","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/2106.05408/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":"2026-07-05T05:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IpA49b4im1H8SN4Y2AhT2vnicHUgsZLE7Mn1JAAGl9BH92IYti7/yBd04V/Ja6tPOuqyhBOt5wbwTzT8r3HbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T12:16:20.953689Z"},"content_sha256":"c275f46f0fa380f9f6e9aaba4f0c01232e6eb0108cb36af7e4bec9cd3c444f4f","schema_version":"1.0","event_id":"sha256:c275f46f0fa380f9f6e9aaba4f0c01232e6eb0108cb36af7e4bec9cd3c444f4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7/bundle.json","state_url":"https://pith.science/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7/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":"2026-07-10T12:16:20Z","links":{"resolver":"https://pith.science/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7","bundle":"https://pith.science/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7/bundle.json","state":"https://pith.science/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIBAKLZIVREECTNRPD4ZH4VDZ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZIBAKLZIVREECTNRPD4ZH4VDZ7","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":"658e872ffe65c435c1c3442ab40e4f22b7b997ae56d5bac4f8ebc91c9deb64b9","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-09T21:55:05Z","title_canon_sha256":"720551ee8a2c944ba144e442505458b598736b88ca96f68419f8631804f41b65"},"schema_version":"1.0","source":{"id":"2106.05408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05408","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05408v1","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05408","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZIBAKLZIVREE","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZIBAKLZIVREECTNR","created_at":"2026-07-05T05:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZIBAKLZI","created_at":"2026-07-05T05:00:37Z"}],"graph_snapshots":[{"event_id":"sha256:c275f46f0fa380f9f6e9aaba4f0c01232e6eb0108cb36af7e4bec9cd3c444f4f","target":"graph","created_at":"2026-07-05T05:00:37Z","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/2106.05408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the merit of transfer learning for two sound recognition problems, i.e., audio tagging and sound event detection. Employing feature fusion, we adapt a baseline system utilizing only spectral acoustic inputs to also make use of pretrained auditory and visual features, extracted from networks built for different tasks and trained with external data. We perform experiments with these modified models on an audiovisual multi-label data set, of which the training partition contains a large number of unlabeled samples and a smaller amount of clips with weak annotations, indicating the clip-l","authors_text":"Hugo Van hamme, Wim Boes","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-09T21:55:05Z","title":"Audiovisual transfer learning for audio tagging and sound event detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05408","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":"sha256:822a708858743a0544a677e9fb06b16b4569af3997d35a643a39c1f27d57b31e","target":"record","created_at":"2026-07-05T05:00:37Z","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":"658e872ffe65c435c1c3442ab40e4f22b7b997ae56d5bac4f8ebc91c9deb64b9","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-09T21:55:05Z","title_canon_sha256":"720551ee8a2c944ba144e442505458b598736b88ca96f68419f8631804f41b65"},"schema_version":"1.0","source":{"id":"2106.05408","kind":"arxiv","version":1}},"canonical_sha256":"ca02052f28ac48414db178f993f2a3cffdd0960b10c6eda1ec2fa3d2b2b46d5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca02052f28ac48414db178f993f2a3cffdd0960b10c6eda1ec2fa3d2b2b46d5e","first_computed_at":"2026-07-05T05:00:37.245255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:37.245255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JdlpsCfFf58GKLMBWRMy9X/fcunGDGDrWB0DUMKyK+SnQWAmaLgTfiUFYoN0PgZeFgnzrafeehlP7siN2gaBAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:37.245707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:822a708858743a0544a677e9fb06b16b4569af3997d35a643a39c1f27d57b31e","sha256:c275f46f0fa380f9f6e9aaba4f0c01232e6eb0108cb36af7e4bec9cd3c444f4f"],"state_sha256":"2fe75cd6140e4099e227422a713f9546f1fe11cb8b95a94f55bdd2df8d58513e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhCiiXg45KUWLMORmVQEM758xZp20F8ETsxPbYWy0jLsZORssdlNAcbQgqHS85TrbKa3VK3tNwyabt/MdewwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T12:16:20.955901Z","bundle_sha256":"fb89df81f6de556ef4b46790c13523591ac36a0382cd7f34a3b8706adbc6c4b5"}}