{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2EFT6OAPZJJXWNVRSZZ7R4FA4V","short_pith_number":"pith:2EFT6OAP","schema_version":"1.0","canonical_sha256":"d10b3f380fca537b36b19673f8f0a0e568edd7ae451629dcfbf963d67d8fb7f1","source":{"kind":"arxiv","id":"2107.09990","version":3},"attestation_state":"computed","paper":{"title":"CL4AC: A Contrastive Loss for Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"H Lilian Tang, Mark D. Plumbley, Qiushi Huang, Tom Ko, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2021-07-21T10:13:02Z","abstract_excerpt":"Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip. As shown in the submissions received for Task 6 of the DCASE 2021 Challenges, this problem has received increasing interest in the community. The existing AAC systems are usually based on an encoder-decoder architecture, where the audio signal is encoded into a latent representation, and aligned with its corresponding text descriptions, then a decoder is used to generate the captions. However, training of an AAC system often encounters the problem of da"},"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":"2107.09990","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T10:13:02Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ff537862f83591a40cc0002a97d9c6697709fd4ca66f04a2acdc2fa56553dfde","abstract_canon_sha256":"def759eff0ccf53fbe4e3dc48c6b44278d4c0c28abb31a698be117f280de2cce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:46.164732Z","signature_b64":"REW7/7yDSZTJzauU+V5DFF99GN8lhtC8speXAKzeOkhkpVDAAje6n9i9EIhv0nbL/MZDrhN1fu7UC8fiJduMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d10b3f380fca537b36b19673f8f0a0e568edd7ae451629dcfbf963d67d8fb7f1","last_reissued_at":"2026-07-05T03:33:46.164299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:46.164299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CL4AC: A Contrastive Loss for Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"H Lilian Tang, Mark D. Plumbley, Qiushi Huang, Tom Ko, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2021-07-21T10:13:02Z","abstract_excerpt":"Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip. As shown in the submissions received for Task 6 of the DCASE 2021 Challenges, this problem has received increasing interest in the community. The existing AAC systems are usually based on an encoder-decoder architecture, where the audio signal is encoded into a latent representation, and aligned with its corresponding text descriptions, then a decoder is used to generate the captions. However, training of an AAC system often encounters the problem of da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09990","kind":"arxiv","version":3},"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/2107.09990/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":"2107.09990","created_at":"2026-07-05T03:33:46.164358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.09990v3","created_at":"2026-07-05T03:33:46.164358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09990","created_at":"2026-07-05T03:33:46.164358+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EFT6OAPZJJX","created_at":"2026-07-05T03:33:46.164358+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EFT6OAPZJJXWNVR","created_at":"2026-07-05T03:33:46.164358+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EFT6OAP","created_at":"2026-07-05T03:33:46.164358+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/2EFT6OAPZJJXWNVRSZZ7R4FA4V","json":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V.json","graph_json":"https://pith.science/api/pith-number/2EFT6OAPZJJXWNVRSZZ7R4FA4V/graph.json","events_json":"https://pith.science/api/pith-number/2EFT6OAPZJJXWNVRSZZ7R4FA4V/events.json","paper":"https://pith.science/paper/2EFT6OAP"},"agent_actions":{"view_html":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V","download_json":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V.json","view_paper":"https://pith.science/paper/2EFT6OAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.09990&json=true","fetch_graph":"https://pith.science/api/pith-number/2EFT6OAPZJJXWNVRSZZ7R4FA4V/graph.json","fetch_events":"https://pith.science/api/pith-number/2EFT6OAPZJJXWNVRSZZ7R4FA4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V/action/storage_attestation","attest_author":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V/action/author_attestation","sign_citation":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V/action/citation_signature","submit_replication":"https://pith.science/pith/2EFT6OAPZJJXWNVRSZZ7R4FA4V/action/replication_record"}},"created_at":"2026-07-05T03:33:46.164358+00:00","updated_at":"2026-07-05T03:33:46.164358+00:00"}