{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TZMQDXTNDOUKFRXZINTHLHWVAK","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":"20656c1642c21748ec3f37a04203fb03e90a062da434ade908f70c667f37ff1f","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T17:59:30Z","title_canon_sha256":"30bec728885e6481746fa29d3662a7c44f8571b3ddafc3d32a9185fdbe01165b"},"schema_version":"1.0","source":{"id":"2102.02779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02779","created_at":"2026-07-05T02:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02779v2","created_at":"2026-07-05T02:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02779","created_at":"2026-07-05T02:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"TZMQDXTNDOUK","created_at":"2026-07-05T02:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"TZMQDXTNDOUKFRXZ","created_at":"2026-07-05T02:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"TZMQDXTN","created_at":"2026-07-05T02:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:6550e58dbb1376b4b4fecc7217911c22c0c1f4fcc1989a756c9836bc963c4812","target":"graph","created_at":"2026-07-05T02:42:29Z","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/2102.02779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for referring expression comprehension, and a language decoder for image captioning, etc. To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation, where our models learn to generate labels in text based on the visu","authors_text":"Hao Tan, Jaemin Cho, Jie Lei, Mohit Bansal","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T17:59:30Z","title":"Unifying Vision-and-Language Tasks via Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02779","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":"sha256:433d447668074add5ae9e5095760907b2ad2ca21019125f3dff8ca7801cb8834","target":"record","created_at":"2026-07-05T02:42:29Z","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":"20656c1642c21748ec3f37a04203fb03e90a062da434ade908f70c667f37ff1f","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-04T17:59:30Z","title_canon_sha256":"30bec728885e6481746fa29d3662a7c44f8571b3ddafc3d32a9185fdbe01165b"},"schema_version":"1.0","source":{"id":"2102.02779","kind":"arxiv","version":2}},"canonical_sha256":"9e5901de6d1ba8a2c6f94366759ed50290e896d16b12eccdf8b3481fe30dbb0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e5901de6d1ba8a2c6f94366759ed50290e896d16b12eccdf8b3481fe30dbb0a","first_computed_at":"2026-07-05T02:42:29.321977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:29.321977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kpM83bEr6WRTxyo4fvGmt0H2/k6FewvqU0shc36y8EfusCrTJFuO+xjbId/umf12j2bYTj8bIzQq3Xo2T2b/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:29.322508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:433d447668074add5ae9e5095760907b2ad2ca21019125f3dff8ca7801cb8834","sha256:6550e58dbb1376b4b4fecc7217911c22c0c1f4fcc1989a756c9836bc963c4812"],"state_sha256":"5a1aa196db16029a98619c2ab144caf6badd175dc104af828ecbb4665fa7becf"}