{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2W7IU3PVILAGWQRWU4225JBTUJ","short_pith_number":"pith:2W7IU3PV","canonical_record":{"source":{"id":"2012.07331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-12-14T08:27:36Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3c4b11fbbbcac0fc6324cbc17209e476316e30e78bb6d16c86300f557757ea02","abstract_canon_sha256":"7e5e0f432eab69e58ce9e13da9bfc30cd95c90530de279f7a098c2bca4a146e3"},"schema_version":"1.0"},"canonical_sha256":"d5be8a6df542c06b4236a735aea433a26311c5d6b84270c23254273738e7baa6","source":{"kind":"arxiv","id":"2012.07331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07331","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07331v1","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07331","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"2W7IU3PVILAG","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"2W7IU3PVILAGWQRW","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"2W7IU3PV","created_at":"2026-07-05T01:59:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2W7IU3PVILAGWQRWU4225JBTUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.07331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-12-14T08:27:36Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3c4b11fbbbcac0fc6324cbc17209e476316e30e78bb6d16c86300f557757ea02","abstract_canon_sha256":"7e5e0f432eab69e58ce9e13da9bfc30cd95c90530de279f7a098c2bca4a146e3"},"schema_version":"1.0"},"canonical_sha256":"d5be8a6df542c06b4236a735aea433a26311c5d6b84270c23254273738e7baa6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:19.440206Z","signature_b64":"L1QaUduFhgO4nBMdeadEV2zCevf6xazocEo8EmRaOlc3tbk7VIX37lV569gRp7jM7D7lmc9q3Fk1qYeEDpFFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5be8a6df542c06b4236a735aea433a26311c5d6b84270c23254273738e7baa6","last_reissued_at":"2026-07-05T01:59:19.439735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:19.439735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.07331","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":"2026-07-05T01:59:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FhQedfxGqREdqWlx5muwm+X4C5A3jJOiyDP0FW1cBLEr4xXCNaeeVzQLavLtPiv13qPKBGsWp6GHazenH5CJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:59:10.094911Z"},"content_sha256":"4a822430f5856829233461d59e3db2689ad5b2db485ccacf3b59e0123bf8cc77","schema_version":"1.0","event_id":"sha256:4a822430f5856829233461d59e3db2689ad5b2db485ccacf3b59e0123bf8cc77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2W7IU3PVILAGWQRWU4225JBTUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Yasunori Ohishi, Yuma Koizumi","submitted_at":"2020-12-14T08:27:36Z","abstract_excerpt":"The goal of audio captioning is to translate input audio into its description using natural language. One of the problems in audio captioning is the lack of training data due to the difficulty in collecting audio-caption pairs by crawling the web. In this study, to overcome this problem, we propose to use a pre-trained large-scale language model. Since an audio input cannot be directly inputted into such a language model, we utilize guidance captions retrieved from a training dataset based on similarities that may exist in different audio. Then, the caption of the audio input is generated by u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07331","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/2012.07331/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":"2026-07-05T01:59:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+NkfnRy0Bvq6p6B+/xBpY2YHIExiO1rJGA3oa55IhLUWR/Z4IFaLp8d1UTwFyHqYvfozhh9IskwI6lBQI79DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:59:10.095893Z"},"content_sha256":"9281eb7455c731a0e9651006cadddf41d74ffd0c75dcd75278831bab44845fe2","schema_version":"1.0","event_id":"sha256:9281eb7455c731a0e9651006cadddf41d74ffd0c75dcd75278831bab44845fe2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2W7IU3PVILAGWQRWU4225JBTUJ/bundle.json","state_url":"https://pith.science/pith/2W7IU3PVILAGWQRWU4225JBTUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2W7IU3PVILAGWQRWU4225JBTUJ/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":"2026-08-15T13:59:10Z","links":{"resolver":"https://pith.science/pith/2W7IU3PVILAGWQRWU4225JBTUJ","bundle":"https://pith.science/pith/2W7IU3PVILAGWQRWU4225JBTUJ/bundle.json","state":"https://pith.science/pith/2W7IU3PVILAGWQRWU4225JBTUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2W7IU3PVILAGWQRWU4225JBTUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2W7IU3PVILAGWQRWU4225JBTUJ","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":"7e5e0f432eab69e58ce9e13da9bfc30cd95c90530de279f7a098c2bca4a146e3","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-12-14T08:27:36Z","title_canon_sha256":"3c4b11fbbbcac0fc6324cbc17209e476316e30e78bb6d16c86300f557757ea02"},"schema_version":"1.0","source":{"id":"2012.07331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07331","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07331v1","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07331","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"2W7IU3PVILAG","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"2W7IU3PVILAGWQRW","created_at":"2026-07-05T01:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"2W7IU3PV","created_at":"2026-07-05T01:59:19Z"}],"graph_snapshots":[{"event_id":"sha256:9281eb7455c731a0e9651006cadddf41d74ffd0c75dcd75278831bab44845fe2","target":"graph","created_at":"2026-07-05T01:59:19Z","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/2012.07331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of audio captioning is to translate input audio into its description using natural language. One of the problems in audio captioning is the lack of training data due to the difficulty in collecting audio-caption pairs by crawling the web. In this study, to overcome this problem, we propose to use a pre-trained large-scale language model. Since an audio input cannot be directly inputted into such a language model, we utilize guidance captions retrieved from a training dataset based on similarities that may exist in different audio. Then, the caption of the audio input is generated by u","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Yasunori Ohishi, Yuma Koizumi","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-12-14T08:27:36Z","title":"Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07331","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":"sha256:4a822430f5856829233461d59e3db2689ad5b2db485ccacf3b59e0123bf8cc77","target":"record","created_at":"2026-07-05T01:59:19Z","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":"7e5e0f432eab69e58ce9e13da9bfc30cd95c90530de279f7a098c2bca4a146e3","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-12-14T08:27:36Z","title_canon_sha256":"3c4b11fbbbcac0fc6324cbc17209e476316e30e78bb6d16c86300f557757ea02"},"schema_version":"1.0","source":{"id":"2012.07331","kind":"arxiv","version":1}},"canonical_sha256":"d5be8a6df542c06b4236a735aea433a26311c5d6b84270c23254273738e7baa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5be8a6df542c06b4236a735aea433a26311c5d6b84270c23254273738e7baa6","first_computed_at":"2026-07-05T01:59:19.439735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:19.439735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L1QaUduFhgO4nBMdeadEV2zCevf6xazocEo8EmRaOlc3tbk7VIX37lV569gRp7jM7D7lmc9q3Fk1qYeEDpFFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:19.440206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.07331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a822430f5856829233461d59e3db2689ad5b2db485ccacf3b59e0123bf8cc77","sha256:9281eb7455c731a0e9651006cadddf41d74ffd0c75dcd75278831bab44845fe2"],"state_sha256":"1b59b7ae6a00423ac9ccd8351ee64cd1299dfa5b4915a42e0e5283f3c447a589"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TUo3pFYXYnrt24o88KRptc8cfVJgoVpVYWQkGtpA0z8lMKi8dgkudW45rv6IkPXOV6mxmDBfbdJXKI0qD34nDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T13:59:10.103431Z","bundle_sha256":"cd573f1ccc73fdaf37a68b04e2ad797e3669ea5db128c5d8f35c421f35e092ef"}}