{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GQQ6NSZWEGLMB5GJGU2Q6AS574","short_pith_number":"pith:GQQ6NSZW","schema_version":"1.0","canonical_sha256":"3421e6cb362196c0f4c935350f025dff1a13382d0fdc63e98653915e9af9fab5","source":{"kind":"arxiv","id":"2102.10772","version":3},"attestation_state":"computed","paper":{"title":"UniT: Multimodal Multitask Learning with a Unified Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Ronghang Hu","submitted_at":"2021-02-22T04:45:06Z","abstract_excerpt":"We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer encoder-decoder architecture, our UniT model encodes each input modality with an encoder and makes predictions on each task with a shared decoder over the encoded input representations, followed by task-specific output heads. The entire model is jointly trained end-to-end with losses from each task. Compared to previous efforts on multi-task learning with transfo"},"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":"2102.10772","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-22T04:45:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"237b81cb96e0442237cbd908d27e7b417fc7d1fd8b046c2dfa55134df29f0e3c","abstract_canon_sha256":"75ed59f1fea4402ff004e21bd0c67872ead5c4d53e473ced88f8b8ab57ce36dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:45.874137Z","signature_b64":"M96zjaXL/91omre6ZOCE06z4RBCXZDGFdwkAPXLGfLBYghO6r76O5QY6m5SbybP9HHJQ71gVrI8VMy20CM9eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3421e6cb362196c0f4c935350f025dff1a13382d0fdc63e98653915e9af9fab5","last_reissued_at":"2026-07-05T03:06:45.873729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:45.873729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniT: Multimodal Multitask Learning with a Unified Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Ronghang Hu","submitted_at":"2021-02-22T04:45:06Z","abstract_excerpt":"We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer encoder-decoder architecture, our UniT model encodes each input modality with an encoder and makes predictions on each task with a shared decoder over the encoded input representations, followed by task-specific output heads. The entire model is jointly trained end-to-end with losses from each task. Compared to previous efforts on multi-task learning with transfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10772","kind":"arxiv","version":3},"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/2102.10772/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":"2102.10772","created_at":"2026-07-05T03:06:45.873786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10772v3","created_at":"2026-07-05T03:06:45.873786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10772","created_at":"2026-07-05T03:06:45.873786+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQQ6NSZWEGLM","created_at":"2026-07-05T03:06:45.873786+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQQ6NSZWEGLMB5GJ","created_at":"2026-07-05T03:06:45.873786+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQQ6NSZW","created_at":"2026-07-05T03:06:45.873786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10540","citing_title":"Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574","json":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574.json","graph_json":"https://pith.science/api/pith-number/GQQ6NSZWEGLMB5GJGU2Q6AS574/graph.json","events_json":"https://pith.science/api/pith-number/GQQ6NSZWEGLMB5GJGU2Q6AS574/events.json","paper":"https://pith.science/paper/GQQ6NSZW"},"agent_actions":{"view_html":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574","download_json":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574.json","view_paper":"https://pith.science/paper/GQQ6NSZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10772&json=true","fetch_graph":"https://pith.science/api/pith-number/GQQ6NSZWEGLMB5GJGU2Q6AS574/graph.json","fetch_events":"https://pith.science/api/pith-number/GQQ6NSZWEGLMB5GJGU2Q6AS574/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/action/storage_attestation","attest_author":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/action/author_attestation","sign_citation":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/action/citation_signature","submit_replication":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/action/replication_record"}},"created_at":"2026-07-05T03:06:45.873786+00:00","updated_at":"2026-07-05T03:06:45.873786+00:00"}