{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6YZWALWPGYNSW6YY67ZGFN7RCP","short_pith_number":"pith:6YZWALWP","canonical_record":{"source":{"id":"2304.08345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T15:08:15Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"e6c8ba09b0b5a7ff81eab039d628140f3149a1cd339fcbc7f6412051bfbbe2f6","abstract_canon_sha256":"329cd2cee8cb5794503beed804fcd3d8e508189f5257d9cc6f4a0f9fd477cb2d"},"schema_version":"1.0"},"canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","source":{"kind":"arxiv","id":"2304.08345","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6YZWALWPGYNSW6YY67ZGFN7RCP","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T15:08:15Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"e6c8ba09b0b5a7ff81eab039d628140f3149a1cd339fcbc7f6412051bfbbe2f6","abstract_canon_sha256":"329cd2cee8cb5794503beed804fcd3d8e508189f5257d9cc6f4a0f9fd477cb2d"},"schema_version":"1.0"},"canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:18.074222Z","signature_b64":"UeqSCpiy6AbiQX8hD5F/ERBoNThSJtRmHB02SsrNT+Q3N0l+1Nt/+m9BBICDtvaL6ZXIDXllXnMJrSnpd/jCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","last_reissued_at":"2026-07-05T09:57:18.073736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:18.073736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08345","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wc1BvS7l//07jBeut5K1JYLFhmeu4EvhS2gtaIwFMfbUZ5a7bSlcY7d22zVp2h3cPsDiYHFw4aUZWyWnjChvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:21:36.883302Z"},"content_sha256":"5165b7fe837a4555ff78e5ffe6f3b207adaa143b918e7cc02f99c47726238659","schema_version":"1.0","event_id":"sha256:5165b7fe837a4555ff78e5ffe6f3b207adaa143b918e7cc02f99c47726238659"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6YZWALWPGYNSW6YY67ZGFN7RCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Jinhui Tang, Longteng Guo, Sihan Chen, Weining Wang, Xingjian He, Xinxin Zhu","submitted_at":"2023-04-17T15:08:15Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08345","kind":"arxiv","version":2},"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/2304.08345/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2iSWGVFbPjyhi5uuD1l9G0NpFr9UMLOjlM/uG0R50HVL+z1Dt6578pA4+sJ2u2c1xAcFCFWqa/afJ3XmhpLmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:21:36.883864Z"},"content_sha256":"2044011dee853f74c10aad4fb5bc315d0b6fb3cc1b285f498fc9903afae3b8ad","schema_version":"1.0","event_id":"sha256:2044011dee853f74c10aad4fb5bc315d0b6fb3cc1b285f498fc9903afae3b8ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/bundle.json","state_url":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T17:21:36Z","links":{"resolver":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP","bundle":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/bundle.json","state":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fkSVvZBtwEijpEZWfxX5UhLJzzVrc5gNCpOs77aFyWgVcxxYgD6i9aUR5jO6D9rYEaZ3GpnHp8MF69aJhOdmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:21:36.888060Z","bundle_sha256":"f5f359a288d26ffa9fb8a41bfac7192e0a7ae6f92cd6dcd19912ed8331ebd5e7"}}