{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GQQ6NSZWEGLMB5GJGU2Q6AS574","short_pith_number":"pith:GQQ6NSZW","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"},"canonical_sha256":"3421e6cb362196c0f4c935350f025dff1a13382d0fdc63e98653915e9af9fab5","source":{"kind":"arxiv","id":"2102.10772","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10772","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10772v3","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10772","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"GQQ6NSZWEGLM","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"GQQ6NSZWEGLMB5GJ","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"GQQ6NSZW","created_at":"2026-07-05T03:06:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GQQ6NSZWEGLMB5GJGU2Q6AS574","target":"record","payload":{"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"},"canonical_sha256":"3421e6cb362196c0f4c935350f025dff1a13382d0fdc63e98653915e9af9fab5","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"},"source_kind":"arxiv","source_id":"2102.10772","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SqsucQIh+Kn0zLjfsmMMkIgucibZxOy0KUU0caDYhRAs/S8foSlJGEIaZ7sn90oOIbrmAqkjmHOUEj461lSqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:30:05.244756Z"},"content_sha256":"baa282bcdbc7add2b903b43997b4721281f1ffeaf2747982a23113422f0704d9","schema_version":"1.0","event_id":"sha256:baa282bcdbc7add2b903b43997b4721281f1ffeaf2747982a23113422f0704d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GQQ6NSZWEGLMB5GJGU2Q6AS574","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:06:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CS7MHIKZ19T4DMlrlyY0LdKwvECrkYMw3BWDQGerE0U6fy0y22M2eN7SdXOhfAYisOiDk+A1w/Bv9MZbhfADAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:30:05.245722Z"},"content_sha256":"92f9bdb9a823bc3582929b81769f7aa881cf253abbc9c8941b5b6f2cd7ec061c","schema_version":"1.0","event_id":"sha256:92f9bdb9a823bc3582929b81769f7aa881cf253abbc9c8941b5b6f2cd7ec061c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/bundle.json","state_url":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/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":"2026-08-14T13:30:05Z","links":{"resolver":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574","bundle":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/bundle.json","state":"https://pith.science/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQQ6NSZWEGLMB5GJGU2Q6AS574/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GQQ6NSZWEGLMB5GJGU2Q6AS574","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":"75ed59f1fea4402ff004e21bd0c67872ead5c4d53e473ced88f8b8ab57ce36dc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-22T04:45:06Z","title_canon_sha256":"237b81cb96e0442237cbd908d27e7b417fc7d1fd8b046c2dfa55134df29f0e3c"},"schema_version":"1.0","source":{"id":"2102.10772","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10772","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10772v3","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10772","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"GQQ6NSZWEGLM","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"GQQ6NSZWEGLMB5GJ","created_at":"2026-07-05T03:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"GQQ6NSZW","created_at":"2026-07-05T03:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:92f9bdb9a823bc3582929b81769f7aa881cf253abbc9c8941b5b6f2cd7ec061c","target":"graph","created_at":"2026-07-05T03:06:45Z","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/2102.10772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amanpreet Singh, Ronghang Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-22T04:45:06Z","title":"UniT: Multimodal Multitask Learning with a Unified Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10772","kind":"arxiv","version":3},"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:baa282bcdbc7add2b903b43997b4721281f1ffeaf2747982a23113422f0704d9","target":"record","created_at":"2026-07-05T03:06:45Z","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":"75ed59f1fea4402ff004e21bd0c67872ead5c4d53e473ced88f8b8ab57ce36dc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-22T04:45:06Z","title_canon_sha256":"237b81cb96e0442237cbd908d27e7b417fc7d1fd8b046c2dfa55134df29f0e3c"},"schema_version":"1.0","source":{"id":"2102.10772","kind":"arxiv","version":3}},"canonical_sha256":"3421e6cb362196c0f4c935350f025dff1a13382d0fdc63e98653915e9af9fab5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3421e6cb362196c0f4c935350f025dff1a13382d0fdc63e98653915e9af9fab5","first_computed_at":"2026-07-05T03:06:45.873729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:45.873729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M96zjaXL/91omre6ZOCE06z4RBCXZDGFdwkAPXLGfLBYghO6r76O5QY6m5SbybP9HHJQ71gVrI8VMy20CM9eCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:45.874137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10772","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baa282bcdbc7add2b903b43997b4721281f1ffeaf2747982a23113422f0704d9","sha256:92f9bdb9a823bc3582929b81769f7aa881cf253abbc9c8941b5b6f2cd7ec061c"],"state_sha256":"6d85dfecd2af331df593b55cb9ebcfd5ff988a91396a2f419bdf631c42ac3867"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OhU+wDOqDx29K4SjC4qXyW1hXigS88tsfEL5D34sm//X+bJD/Njkrcj7TbDYNB+LmW5UCFCKqX42zNN/OfPpBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:30:05.251822Z","bundle_sha256":"528646111bdddd4c8c5361d18ce50d50c1cc708c1f8ef37b2103e2f7f9841b17"}}