{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QVOTGORT5NYATU6H2FUJ5NARAQ","short_pith_number":"pith:QVOTGORT","canonical_record":{"source":{"id":"1912.02615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-12-02T15:26:37Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"48d7efdc548033660db65f6f0076bbcd8865d9189f8fe4913fb83a87b89c82a9","abstract_canon_sha256":"5714e86387e07b3376d83cd34060c15c778d18c20a4cb89e4d1ad2eb0dace7a7"},"schema_version":"1.0"},"canonical_sha256":"855d333a33eb7009d3c7d1689eb411043e39643e93c9975e7daeecb2e7a2eb6a","source":{"kind":"arxiv","id":"1912.02615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02615","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02615v1","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02615","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"QVOTGORT5NYA","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"QVOTGORT5NYATU6H","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"QVOTGORT","created_at":"2026-07-05T00:24:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QVOTGORT5NYATU6H2FUJ5NARAQ","target":"record","payload":{"canonical_record":{"source":{"id":"1912.02615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-12-02T15:26:37Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"48d7efdc548033660db65f6f0076bbcd8865d9189f8fe4913fb83a87b89c82a9","abstract_canon_sha256":"5714e86387e07b3376d83cd34060c15c778d18c20a4cb89e4d1ad2eb0dace7a7"},"schema_version":"1.0"},"canonical_sha256":"855d333a33eb7009d3c7d1689eb411043e39643e93c9975e7daeecb2e7a2eb6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:15.411914Z","signature_b64":"ryxLXuCCuBqB5t8OKsKRWMTIrhuqgpoiS1t2nANr5HI+CVcco1SHTJHP78yALflP4yrKfpffR5hqikatVk/0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"855d333a33eb7009d3c7d1689eb411043e39643e93c9975e7daeecb2e7a2eb6a","last_reissued_at":"2026-07-05T00:24:15.411502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:15.411502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.02615","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":"2026-07-05T00:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vfd2Fm8HqI2j/YLg+8ox+FBHF+Wf8vswJqoiPzpKd/SuZzu7uGYVBH56UK246aad2E9Mqt7RYig6eipYb9cTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:19:33.058960Z"},"content_sha256":"1aab97bf9dae0ad03a980303b5ec230b67e3507202ee13e8b888e739bd3148e4","schema_version":"1.0","event_id":"sha256:1aab97bf9dae0ad03a980303b5ec230b67e3507202ee13e8b888e739bd3148e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QVOTGORT5NYATU6H2FUJ5NARAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Wim Boes","submitted_at":"2019-12-02T15:26:37Z","abstract_excerpt":"We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation. We modify this attention-based feedforward structure in such a way that allows the resulting model to use audio as well as video to compute sound event predictions. We perform extensive experiments with these adapted transformers on an audiovisual data set, obtained by appending relevant visual information to an existing large-scale weakly labeled audio collection. The employed multi-label data contains clip-level annotation indicating th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02615","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/1912.02615/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":"2026-07-05T00:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xu0pUJdHF41qlBTzw+LKgHjOpFelOKukZoIzmTqaHXYOaqjGzAdZe26L+yPNoDYhy8TLbSAoJBNKam///x4LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:19:33.059498Z"},"content_sha256":"4fd2e5fdf6d87a74abc3fe4cee4d3177c1f0eeb7a100e8d5e34897e472903559","schema_version":"1.0","event_id":"sha256:4fd2e5fdf6d87a74abc3fe4cee4d3177c1f0eeb7a100e8d5e34897e472903559"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVOTGORT5NYATU6H2FUJ5NARAQ/bundle.json","state_url":"https://pith.science/pith/QVOTGORT5NYATU6H2FUJ5NARAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVOTGORT5NYATU6H2FUJ5NARAQ/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":"2026-08-03T16:19:33Z","links":{"resolver":"https://pith.science/pith/QVOTGORT5NYATU6H2FUJ5NARAQ","bundle":"https://pith.science/pith/QVOTGORT5NYATU6H2FUJ5NARAQ/bundle.json","state":"https://pith.science/pith/QVOTGORT5NYATU6H2FUJ5NARAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVOTGORT5NYATU6H2FUJ5NARAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QVOTGORT5NYATU6H2FUJ5NARAQ","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":"5714e86387e07b3376d83cd34060c15c778d18c20a4cb89e4d1ad2eb0dace7a7","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-12-02T15:26:37Z","title_canon_sha256":"48d7efdc548033660db65f6f0076bbcd8865d9189f8fe4913fb83a87b89c82a9"},"schema_version":"1.0","source":{"id":"1912.02615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02615","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02615v1","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02615","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"QVOTGORT5NYA","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"QVOTGORT5NYATU6H","created_at":"2026-07-05T00:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"QVOTGORT","created_at":"2026-07-05T00:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:4fd2e5fdf6d87a74abc3fe4cee4d3177c1f0eeb7a100e8d5e34897e472903559","target":"graph","created_at":"2026-07-05T00:24:15Z","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/1912.02615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation. We modify this attention-based feedforward structure in such a way that allows the resulting model to use audio as well as video to compute sound event predictions. We perform extensive experiments with these adapted transformers on an audiovisual data set, obtained by appending relevant visual information to an existing large-scale weakly labeled audio collection. The employed multi-label data contains clip-level annotation indicating th","authors_text":"Hugo Van hamme, Wim Boes","cross_cats":["cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-12-02T15:26:37Z","title":"Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02615","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":"sha256:1aab97bf9dae0ad03a980303b5ec230b67e3507202ee13e8b888e739bd3148e4","target":"record","created_at":"2026-07-05T00:24:15Z","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":"5714e86387e07b3376d83cd34060c15c778d18c20a4cb89e4d1ad2eb0dace7a7","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-12-02T15:26:37Z","title_canon_sha256":"48d7efdc548033660db65f6f0076bbcd8865d9189f8fe4913fb83a87b89c82a9"},"schema_version":"1.0","source":{"id":"1912.02615","kind":"arxiv","version":1}},"canonical_sha256":"855d333a33eb7009d3c7d1689eb411043e39643e93c9975e7daeecb2e7a2eb6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"855d333a33eb7009d3c7d1689eb411043e39643e93c9975e7daeecb2e7a2eb6a","first_computed_at":"2026-07-05T00:24:15.411502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:15.411502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ryxLXuCCuBqB5t8OKsKRWMTIrhuqgpoiS1t2nANr5HI+CVcco1SHTJHP78yALflP4yrKfpffR5hqikatVk/0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:15.411914Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aab97bf9dae0ad03a980303b5ec230b67e3507202ee13e8b888e739bd3148e4","sha256:4fd2e5fdf6d87a74abc3fe4cee4d3177c1f0eeb7a100e8d5e34897e472903559"],"state_sha256":"5055ed9546f333fbbad9c0ca85064f214980f4697d10a1374a757cd4569c0e05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZOMcXBTNgY2VTuoqDpJn1GOKdVm8dH76VwjUnhS1tktLbn/8ZUFHC2C1pSbL2Dqxm7V5RzXUOdKEPxw6bJD0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:19:33.062731Z","bundle_sha256":"42a88778f72925b485523765c7902cd706e3c6c09fbf464347c30aace0d8c834"}}