{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MQPKSZVYAUEDKQKO3U34CPVGEX","short_pith_number":"pith:MQPKSZVY","schema_version":"1.0","canonical_sha256":"641ea966b8050835414edd37c13ea625e2ba01ee9f22b65ded9f0b17ce368902","source":{"kind":"arxiv","id":"2202.03052","version":2},"attestation_state":"computed","paper":{"title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"An Yang, Chang Zhou, Hongxia Yang, Jianxin Ma, Jingren Zhou, Junyang Lin, Peng Wang, Rui Men, Shuai Bai, Zhikang Li","submitted_at":"2022-02-07T10:38:21Z","abstract_excerpt":"In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.03052","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-07T10:38:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"146805c20a5b62155362ae5595ab7c64b22c4737ecf1849353ca303eace136e1","abstract_canon_sha256":"14de80853d0fd4832eedbe95e6a2503acad8c06593e3d08633cc8d66d5f23097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:09.917152Z","signature_b64":"qNSJpfkbi7w1SGmQraFv8Xr+SajTJZ9psfeR1cBzzEa8bctqjZGMufYDDtiJgwWM4MBBBnSvYDQFqypWe0rXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641ea966b8050835414edd37c13ea625e2ba01ee9f22b65ded9f0b17ce368902","last_reissued_at":"2026-07-05T04:28:09.916683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:09.916683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"An Yang, Chang Zhou, Hongxia Yang, Jianxin Ma, Jingren Zhou, Junyang Lin, Peng Wang, Rui Men, Shuai Bai, Zhikang Li","submitted_at":"2022-02-07T10:38:21Z","abstract_excerpt":"In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03052","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/2202.03052/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.03052","created_at":"2026-07-05T04:28:09.916742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03052v2","created_at":"2026-07-05T04:28:09.916742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03052","created_at":"2026-07-05T04:28:09.916742+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQPKSZVYAUED","created_at":"2026-07-05T04:28:09.916742+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQPKSZVYAUEDKQKO","created_at":"2026-07-05T04:28:09.916742+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQPKSZVY","created_at":"2026-07-05T04:28:09.916742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.08128","citing_title":"ViperGPT: Visual Inference via Python Execution for Reasoning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2209.06794","citing_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01917","citing_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX","json":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX.json","graph_json":"https://pith.science/api/pith-number/MQPKSZVYAUEDKQKO3U34CPVGEX/graph.json","events_json":"https://pith.science/api/pith-number/MQPKSZVYAUEDKQKO3U34CPVGEX/events.json","paper":"https://pith.science/paper/MQPKSZVY"},"agent_actions":{"view_html":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX","download_json":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX.json","view_paper":"https://pith.science/paper/MQPKSZVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03052&json=true","fetch_graph":"https://pith.science/api/pith-number/MQPKSZVYAUEDKQKO3U34CPVGEX/graph.json","fetch_events":"https://pith.science/api/pith-number/MQPKSZVYAUEDKQKO3U34CPVGEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX/action/storage_attestation","attest_author":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX/action/author_attestation","sign_citation":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX/action/citation_signature","submit_replication":"https://pith.science/pith/MQPKSZVYAUEDKQKO3U34CPVGEX/action/replication_record"}},"created_at":"2026-07-05T04:28:09.916742+00:00","updated_at":"2026-07-05T04:28:09.916742+00:00"}