{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AZKTF7ND4BBU67Z7LULXQQF2HB","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":"5a4a5424be9b36724a0140fc85d27f9b2afa045abb2c12731f4cf0226694751c","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-21T09:10:10Z","title_canon_sha256":"e3c4af04fccfddc572dfa038191a66674de4362b5b4878b623f2e16e786200af"},"schema_version":"1.0","source":{"id":"2211.11275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11275","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11275v2","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11275","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_12","alias_value":"AZKTF7ND4BBU","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_16","alias_value":"AZKTF7ND4BBU67Z7","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_8","alias_value":"AZKTF7ND","created_at":"2026-07-05T06:11:43Z"}],"graph_snapshots":[{"event_id":"sha256:215f76395cdf9dbd5cdb4d69745746a41d9418b53a1b21438613ad90daaf4d70","target":"graph","created_at":"2026-07-05T06:11:43Z","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/2211.11275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e.g., vision, text. How to design a unified framework to integrate different modal information and leverage different resources (e.g., visual-audio pairs, audio-text pairs, unlabeled speech, and unlabeled text) to facilitate speech representation learning was not well explored. In this paper, we propose a unified cross-modal representation learning framework VATLM (Visual-Audio-Text Language Model). The proposed VATLM employs a uni","authors_text":"Binxing Jiao, Daxin Jiang, Furu Wei, Jie Zhang, Jinyu Li, Lirong Dai, Long Zhou, Qiushi Zhu, Shujie Liu, Ziqiang Zhang","cross_cats":["cs.AI","cs.CL","cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-21T09:10:10Z","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11275","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:a45094fb1cfd21f1a884e7ec489dd9062000f8fdaeb8bdc210931523d483bb18","target":"record","created_at":"2026-07-05T06:11:43Z","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":"5a4a5424be9b36724a0140fc85d27f9b2afa045abb2c12731f4cf0226694751c","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-21T09:10:10Z","title_canon_sha256":"e3c4af04fccfddc572dfa038191a66674de4362b5b4878b623f2e16e786200af"},"schema_version":"1.0","source":{"id":"2211.11275","kind":"arxiv","version":2}},"canonical_sha256":"065532fda3e0434f7f3f5d177840ba387d884c65f02ba7e2f302a80ddd0ab82a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065532fda3e0434f7f3f5d177840ba387d884c65f02ba7e2f302a80ddd0ab82a","first_computed_at":"2026-07-05T06:11:43.225735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:43.225735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ebLAedz0/1D1UjF2fwmOzJLdK0OY1xT6MUxvbO1+JGTR11L30N+z7Q1TsgtW946RUuhq39dvqd+ZSRhETrK9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:43.226228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a45094fb1cfd21f1a884e7ec489dd9062000f8fdaeb8bdc210931523d483bb18","sha256:215f76395cdf9dbd5cdb4d69745746a41d9418b53a1b21438613ad90daaf4d70"],"state_sha256":"f229bbecd52488ec8d51552d41725a835e5fa97d184810dc25f524812101b201"}