{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PBSCI72ORHM6BRNVQSLJ5B3K7V","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":"d08eea59546023abfd1a9a1b7c5c3d73d3e2de912f9c223fc5326b40d15ad81d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-09-01T04:18:19Z","title_canon_sha256":"91380f0a187728085ed964cf93c2857014f8f649b2906eb28596740463390456"},"schema_version":"1.0","source":{"id":"2109.00181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00181","created_at":"2026-07-05T03:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00181v1","created_at":"2026-07-05T03:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00181","created_at":"2026-07-05T03:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"PBSCI72ORHM6","created_at":"2026-07-05T03:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"PBSCI72ORHM6BRNV","created_at":"2026-07-05T03:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"PBSCI72O","created_at":"2026-07-05T03:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:72adbffe19b33f6b3bed17d83a3241937211d1c8c5112d131aedf74f6cf9930e","target":"graph","created_at":"2026-07-05T03:10:43Z","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/2109.00181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms. However, these models are facing challenges of overfitting with limited labels and low model generalization abilities. In this paper, we present a Cross-modal Transformer for Audio-and-Language, i.e., CTAL, which aims to learn the intra-modality and inter-modality connections between audio and language through two proxy tasks on a large amount of audio-and-language pairs: masked language modeling and masked cross-modal acoustic modeling. After fine-tuning our pre-trained model on m","authors_text":"Hang Li, Tianqiao Liu, Wenbiao Ding, Yu Kang, Zitao Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-09-01T04:18:19Z","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00181","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:f3e005919f2164030bcfc5327b11b5dcba6867e9dddd205ee07595f088c94a36","target":"record","created_at":"2026-07-05T03:10:43Z","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":"d08eea59546023abfd1a9a1b7c5c3d73d3e2de912f9c223fc5326b40d15ad81d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-09-01T04:18:19Z","title_canon_sha256":"91380f0a187728085ed964cf93c2857014f8f649b2906eb28596740463390456"},"schema_version":"1.0","source":{"id":"2109.00181","kind":"arxiv","version":1}},"canonical_sha256":"7864247f4e89d9e0c5b584969e876afd5117f79101d34584e8bf0eafc2b7a487","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7864247f4e89d9e0c5b584969e876afd5117f79101d34584e8bf0eafc2b7a487","first_computed_at":"2026-07-05T03:10:43.574970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:10:43.574970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7zF5k0F9qsVxgHiemjQcRI2zlmd27ypWWDlnnoKRqJmX1ocZR2SfyGGLayLs4utODr+jwKhfNMYVEtU0BR0cCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:10:43.575475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.00181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3e005919f2164030bcfc5327b11b5dcba6867e9dddd205ee07595f088c94a36","sha256:72adbffe19b33f6b3bed17d83a3241937211d1c8c5112d131aedf74f6cf9930e"],"state_sha256":"e1a9692990d0d35638acb0dd4962180c2e5bf893152af47404a6ca64932cb5c4"}