{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:X4RYTQJX2QMIYUOJBJJTN33YGX","short_pith_number":"pith:X4RYTQJX","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"},"canonical_sha256":"bf2389c137d4188c51c90a5336ef7835f070ed6874e78c5e06d0ac5e49f10f7e","source":{"kind":"arxiv","id":"1706.10006","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:X4RYTQJX2QMIYUOJBJJTN33YGX","target":"record","payload":{"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"},"canonical_sha256":"bf2389c137d4188c51c90a5336ef7835f070ed6874e78c5e06d0ac5e49f10f7e","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"},"source_kind":"arxiv","source_id":"1706.10006","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jaHoYJq9WgBiiPVUCj9ZdpTp4dXslZ8iqGA0EZiUERa5FqkOPbPzOPJSSuSIhF+38eAe+39MdwrxUT4fjOmeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:27:07.575094Z"},"content_sha256":"a6d57a6faece0324ca90831b6ff78e2b94c9260281728cc8619b725c01039e21","schema_version":"1.0","event_id":"sha256:a6d57a6faece0324ca90831b6ff78e2b94c9260281728cc8619b725c01039e21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:X4RYTQJX2QMIYUOJBJJTN33YGX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81ydUUwFwKrDjy3EjVav2dEjHXf5M1ShQBrUiAcP0B7AkcQNKsLegbB22931jXKL0DMJaTi44gEhjzH44aa+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:27:07.575786Z"},"content_sha256":"7eea370817ec4c5627392808ee077d899f719f6ca59182c950159d81d9662ea2","schema_version":"1.0","event_id":"sha256:7eea370817ec4c5627392808ee077d899f719f6ca59182c950159d81d9662ea2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/bundle.json","state_url":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/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":"2026-05-30T09:27:07Z","links":{"resolver":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX","bundle":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/bundle.json","state":"https://pith.science/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4RYTQJX2QMIYUOJBJJTN33YGX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ol5cYZ6VyHKZb0kprrKlyOeV6e8ro6RiLqGeq8OVtBj1iMYV+dViqArqGM3MGu4KK06cye1FhoAgNAyQQvfQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:27:07.579501Z","bundle_sha256":"b7928bba349ff48b547e1ebcf41056337375f97adbaf0a21b2407d7b9a8e8837"}}