{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6YZWALWPGYNSW6YY67ZGFN7RCP","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":"329cd2cee8cb5794503beed804fcd3d8e508189f5257d9cc6f4a0f9fd477cb2d","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T15:08:15Z","title_canon_sha256":"e6c8ba09b0b5a7ff81eab039d628140f3149a1cd339fcbc7f6412051bfbbe2f6"},"schema_version":"1.0","source":{"id":"2304.08345","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08345","created_at":"2026-07-05T09:57:18Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08345v2","created_at":"2026-07-05T09:57:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08345","created_at":"2026-07-05T09:57:18Z"},{"alias_kind":"pith_short_12","alias_value":"6YZWALWPGYNS","created_at":"2026-07-05T09:57:18Z"},{"alias_kind":"pith_short_16","alias_value":"6YZWALWPGYNSW6YY","created_at":"2026-07-05T09:57:18Z"},{"alias_kind":"pith_short_8","alias_value":"6YZWALWP","created_at":"2026-07-05T09:57:18Z"}],"graph_snapshots":[{"event_id":"sha256:2044011dee853f74c10aad4fb5bc315d0b6fb3cc1b285f498fc9903afae3b8ad","target":"graph","created_at":"2026-07-05T09:57:18Z","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/2304.08345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner. It contains three separate encoders for single modality representations, and a decoder for multimodal conditional text generation. We design two pretext tasks to pretrain VALOR model, including Multimodal Grouping Alignment (MGA) and Multimodal Grouping Captioning (MGC). MGA projects vision, language and ","authors_text":"Jing Liu, Jinhui Tang, Longteng Guo, Sihan Chen, Weining Wang, Xingjian He, Xinxin Zhu","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T15:08:15Z","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08345","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":"sha256:5165b7fe837a4555ff78e5ffe6f3b207adaa143b918e7cc02f99c47726238659","target":"record","created_at":"2026-07-05T09:57:18Z","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":"329cd2cee8cb5794503beed804fcd3d8e508189f5257d9cc6f4a0f9fd477cb2d","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T15:08:15Z","title_canon_sha256":"e6c8ba09b0b5a7ff81eab039d628140f3149a1cd339fcbc7f6412051bfbbe2f6"},"schema_version":"1.0","source":{"id":"2304.08345","kind":"arxiv","version":2}},"canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","first_computed_at":"2026-07-05T09:57:18.073736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:18.073736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UeqSCpiy6AbiQX8hD5F/ERBoNThSJtRmHB02SsrNT+Q3N0l+1Nt/+m9BBICDtvaL6ZXIDXllXnMJrSnpd/jCBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:18.074222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08345","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5165b7fe837a4555ff78e5ffe6f3b207adaa143b918e7cc02f99c47726238659","sha256:2044011dee853f74c10aad4fb5bc315d0b6fb3cc1b285f498fc9903afae3b8ad"],"state_sha256":"1903d7902b238acbb4b608453610c1a14f0fcb29170d8eff6854631ec5c96948"}