{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:X4RYTQJX2QMIYUOJBJJTN33YGX","short_pith_number":"pith:X4RYTQJX","schema_version":"1.0","canonical_sha256":"bf2389c137d4188c51c90a5336ef7835f070ed6874e78c5e06d0ac5e49f10f7e","source":{"kind":"arxiv","id":"1706.10006","version":2},"attestation_state":"computed","paper":{"title":"Automated Audio Captioning with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2017-06-30T02:55:55Z","abstract_excerpt":"We present the first approach to automated audio captioning. We employ an encoder-decoder scheme with an alignment model in between. The input to the encoder is a sequence of log mel-band energies calculated from an audio file, while the output is a sequence of words, i.e. a caption. The encoder is a multi-layered, bi-directional gated recurrent unit (GRU) and the decoder a multi-layered GRU with a classification layer connected to the last GRU of the decoder. The classification layer and the alignment model are fully connected layers with shared weights between timesteps. The proposed method "},"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":"1706.10006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-06-30T02:55:55Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"60c91dff856706ba4e90cc526003fd47089ec89291f8f9f3a168bc410cb20199","abstract_canon_sha256":"902e49fbb79b475de8a7d457711f29af30601dc93f4bb07371c0cf952d0890e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:08.997707Z","signature_b64":"DmOhxrn4IxOCCN5VV5rPTFCUTibJ+H232AgQ8pWx4mx6vMkFM8YPIYNG3JoHrLCBSjXHcnDpEarISY/7N1h6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf2389c137d4188c51c90a5336ef7835f070ed6874e78c5e06d0ac5e49f10f7e","last_reissued_at":"2026-05-18T00:32:08.996930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:08.996930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Audio Captioning with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen","submitted_at":"2017-06-30T02:55:55Z","abstract_excerpt":"We present the first approach to automated audio captioning. We employ an encoder-decoder scheme with an alignment model in between. The input to the encoder is a sequence of log mel-band energies calculated from an audio file, while the output is a sequence of words, i.e. a caption. The encoder is a multi-layered, bi-directional gated recurrent unit (GRU) and the decoder a multi-layered GRU with a classification layer connected to the last GRU of the decoder. The classification layer and the alignment model are fully connected layers with shared weights between timesteps. The proposed method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.10006","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1706.10006","created_at":"2026-05-18T00:32:08.997052+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.10006v2","created_at":"2026-05-18T00:32:08.997052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.10006","created_at":"2026-05-18T00:32:08.997052+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4RYTQJX2QMI","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4RYTQJX2QMIYUOJ","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4RYTQJX","created_at":"2026-05-18T12:31:53.515858+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/X4RYTQJX2QMIYUOJBJJTN33YGX","json":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX.json","graph_json":"https://pith.science/api/pith-number/X4RYTQJX2QMIYUOJBJJTN33YGX/graph.json","events_json":"https://pith.science/api/pith-number/X4RYTQJX2QMIYUOJBJJTN33YGX/events.json","paper":"https://pith.science/paper/X4RYTQJX"},"agent_actions":{"view_html":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX","download_json":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX.json","view_paper":"https://pith.science/paper/X4RYTQJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.10006&json=true","fetch_graph":"https://pith.science/api/pith-number/X4RYTQJX2QMIYUOJBJJTN33YGX/graph.json","fetch_events":"https://pith.science/api/pith-number/X4RYTQJX2QMIYUOJBJJTN33YGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/action/storage_attestation","attest_author":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/action/author_attestation","sign_citation":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/action/citation_signature","submit_replication":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/action/replication_record"}},"created_at":"2026-05-18T00:32:08.997052+00:00","updated_at":"2026-05-18T00:32:08.997052+00:00"}