{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2EFT6OAPZJJXWNVRSZZ7R4FA4V","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":"def759eff0ccf53fbe4e3dc48c6b44278d4c0c28abb31a698be117f280de2cce","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T10:13:02Z","title_canon_sha256":"ff537862f83591a40cc0002a97d9c6697709fd4ca66f04a2acdc2fa56553dfde"},"schema_version":"1.0","source":{"id":"2107.09990","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09990","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09990v3","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09990","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_12","alias_value":"2EFT6OAPZJJX","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_16","alias_value":"2EFT6OAPZJJXWNVR","created_at":"2026-07-05T03:33:46Z"},{"alias_kind":"pith_short_8","alias_value":"2EFT6OAP","created_at":"2026-07-05T03:33:46Z"}],"graph_snapshots":[{"event_id":"sha256:53297598539b6ba1006670ed692b2888ccf7ee810316ac597552343ba77862be","target":"graph","created_at":"2026-07-05T03:33:46Z","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/2107.09990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"H Lilian Tang, Mark D. Plumbley, Qiushi Huang, Tom Ko, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T10:13:02Z","title":"CL4AC: A Contrastive Loss for Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09990","kind":"arxiv","version":3},"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":"sha256:0723754f17eebc89092d7ad232c0de037e6ee37bedec141fb3bfe77afcd61bb9","target":"record","created_at":"2026-07-05T03:33:46Z","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":"def759eff0ccf53fbe4e3dc48c6b44278d4c0c28abb31a698be117f280de2cce","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T10:13:02Z","title_canon_sha256":"ff537862f83591a40cc0002a97d9c6697709fd4ca66f04a2acdc2fa56553dfde"},"schema_version":"1.0","source":{"id":"2107.09990","kind":"arxiv","version":3}},"canonical_sha256":"d10b3f380fca537b36b19673f8f0a0e568edd7ae451629dcfbf963d67d8fb7f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d10b3f380fca537b36b19673f8f0a0e568edd7ae451629dcfbf963d67d8fb7f1","first_computed_at":"2026-07-05T03:33:46.164299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:46.164299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"REW7/7yDSZTJzauU+V5DFF99GN8lhtC8speXAKzeOkhkpVDAAje6n9i9EIhv0nbL/MZDrhN1fu7UC8fiJduMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:46.164732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09990","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0723754f17eebc89092d7ad232c0de037e6ee37bedec141fb3bfe77afcd61bb9","sha256:53297598539b6ba1006670ed692b2888ccf7ee810316ac597552343ba77862be"],"state_sha256":"3544171f029d02732a755d2075f24b11ec5f3b63255c787da1517dddd97d6197"}