{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:X4RYTQJX2QMIYUOJBJJTN33YGX","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":"902e49fbb79b475de8a7d457711f29af30601dc93f4bb07371c0cf952d0890e3","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-06-30T02:55:55Z","title_canon_sha256":"60c91dff856706ba4e90cc526003fd47089ec89291f8f9f3a168bc410cb20199"},"schema_version":"1.0","source":{"id":"1706.10006","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.10006","created_at":"2026-05-18T00:32:08Z"},{"alias_kind":"arxiv_version","alias_value":"1706.10006v2","created_at":"2026-05-18T00:32:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.10006","created_at":"2026-05-18T00:32:08Z"},{"alias_kind":"pith_short_12","alias_value":"X4RYTQJX2QMI","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X4RYTQJX2QMIYUOJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X4RYTQJX","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:7eea370817ec4c5627392808ee077d899f719f6ca59182c950159d81d9662ea2","target":"graph","created_at":"2026-05-18T00:32:08Z","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"},"paper":{"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 ","authors_text":"Konstantinos Drossos, Sharath Adavanne, Tuomas Virtanen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-06-30T02:55:55Z","title":"Automated Audio Captioning with Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.10006","kind":"arxiv","version":2},"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:a6d57a6faece0324ca90831b6ff78e2b94c9260281728cc8619b725c01039e21","target":"record","created_at":"2026-05-18T00:32:08Z","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":"902e49fbb79b475de8a7d457711f29af30601dc93f4bb07371c0cf952d0890e3","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-06-30T02:55:55Z","title_canon_sha256":"60c91dff856706ba4e90cc526003fd47089ec89291f8f9f3a168bc410cb20199"},"schema_version":"1.0","source":{"id":"1706.10006","kind":"arxiv","version":2}},"canonical_sha256":"bf2389c137d4188c51c90a5336ef7835f070ed6874e78c5e06d0ac5e49f10f7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf2389c137d4188c51c90a5336ef7835f070ed6874e78c5e06d0ac5e49f10f7e","first_computed_at":"2026-05-18T00:32:08.996930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:08.996930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DmOhxrn4IxOCCN5VV5rPTFCUTibJ+H232AgQ8pWx4mx6vMkFM8YPIYNG3JoHrLCBSjXHcnDpEarISY/7N1h6AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:08.997707Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.10006","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6d57a6faece0324ca90831b6ff78e2b94c9260281728cc8619b725c01039e21","sha256:7eea370817ec4c5627392808ee077d899f719f6ca59182c950159d81d9662ea2"],"state_sha256":"9c38330d7e0c5969d76794685f1f3c52f845e58341a64ced79ae27faa08852f7"}