{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PHQTTH7ITJLTA26GHIOQJM7IEU","short_pith_number":"pith:PHQTTH7I","schema_version":"1.0","canonical_sha256":"79e1399fe89a57306bc63a1d04b3e825245b5b7a0d65b72a0698c3e65667d5e4","source":{"kind":"arxiv","id":"2311.01526","version":1},"attestation_state":"computed","paper":{"title":"ATGNN: Audio Tagging Graph Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Christian J. Steinmetz, Dan Stowell, Emmanouil Benetos, Huy Phan, Shubhr Singh","submitted_at":"2023-11-02T18:19:26Z","abstract_excerpt":"Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited. Transformers on the other hand are able to map global context through self-attention, but treat the spectrogram as a sequence of patches which is not flexible enough to capture irregular audio objects. In this work, we treat the spectrogram in a more flexible way by considering it as graph structure and process it with a novel graph neural architecture called ATG"},"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":"2311.01526","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-02T18:19:26Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"1f1b5a62de556ee485d942eb48047b0db957d88e280ca39096bdc26a019e81b8","abstract_canon_sha256":"e33f9bf7bf74371729ab30983ce4458679a365fa7e8726574745b7d9cc2f87e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:30.777773Z","signature_b64":"m7Ab609f1VbSa/pxHF2ZS2QPKpudvNLtpSR7qugjGbUxEyc40FvDvkOqvNGpeiR967NCrnFuAFKHVg4kzjpxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79e1399fe89a57306bc63a1d04b3e825245b5b7a0d65b72a0698c3e65667d5e4","last_reissued_at":"2026-07-05T07:08:30.777299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:30.777299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ATGNN: Audio Tagging Graph Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Christian J. Steinmetz, Dan Stowell, Emmanouil Benetos, Huy Phan, Shubhr Singh","submitted_at":"2023-11-02T18:19:26Z","abstract_excerpt":"Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited. Transformers on the other hand are able to map global context through self-attention, but treat the spectrogram as a sequence of patches which is not flexible enough to capture irregular audio objects. In this work, we treat the spectrogram in a more flexible way by considering it as graph structure and process it with a novel graph neural architecture called ATG"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01526","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/2311.01526/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":"2311.01526","created_at":"2026-07-05T07:08:30.777364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01526v1","created_at":"2026-07-05T07:08:30.777364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01526","created_at":"2026-07-05T07:08:30.777364+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHQTTH7ITJLT","created_at":"2026-07-05T07:08:30.777364+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHQTTH7ITJLTA26G","created_at":"2026-07-05T07:08:30.777364+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHQTTH7I","created_at":"2026-07-05T07:08:30.777364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU","json":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU.json","graph_json":"https://pith.science/api/pith-number/PHQTTH7ITJLTA26GHIOQJM7IEU/graph.json","events_json":"https://pith.science/api/pith-number/PHQTTH7ITJLTA26GHIOQJM7IEU/events.json","paper":"https://pith.science/paper/PHQTTH7I"},"agent_actions":{"view_html":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU","download_json":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU.json","view_paper":"https://pith.science/paper/PHQTTH7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01526&json=true","fetch_graph":"https://pith.science/api/pith-number/PHQTTH7ITJLTA26GHIOQJM7IEU/graph.json","fetch_events":"https://pith.science/api/pith-number/PHQTTH7ITJLTA26GHIOQJM7IEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU/action/storage_attestation","attest_author":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU/action/author_attestation","sign_citation":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU/action/citation_signature","submit_replication":"https://pith.science/pith/PHQTTH7ITJLTA26GHIOQJM7IEU/action/replication_record"}},"created_at":"2026-07-05T07:08:30.777364+00:00","updated_at":"2026-07-05T07:08:30.777364+00:00"}