{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BLDT2QBLPTADLSEJGXC7HACBNN","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":"63bd291f7586ac522c336e3c99de9b7fde7a1ef7b8280b64904068991dcf8721","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T00:20:55Z","title_canon_sha256":"9058cc91ef1d319629353b97047175007ddc2d02115df2427f3840c6899e5be4"},"schema_version":"1.0","source":{"id":"2112.07074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07074","created_at":"2026-07-05T03:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07074v1","created_at":"2026-07-05T03:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07074","created_at":"2026-07-05T03:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"BLDT2QBLPTAD","created_at":"2026-07-05T03:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"BLDT2QBLPTADLSEJ","created_at":"2026-07-05T03:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"BLDT2QBL","created_at":"2026-07-05T03:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:1f2f0fbe644868a77a25465068d8eaf0eb945ef76d321ae1d01f88043c9a0624","target":"graph","created_at":"2026-07-05T03:40:20Z","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/2112.07074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific tokenizers, a shared transformer encoder, and task-specific output heads. To efficiently pre-train the proposed model jointly on unpaired images and text, we propose two novel techniques: (i) We employ the separately-trained BERT and ViT models as teachers and apply knowledge distillation to provide additional, accurate supervision signals for the joint training; ","authors_text":"Boqing Gong, Dan Kondratyuk, Matthew Brown, Ming-Hsuan Yang, Qing Li, Xianzhi Du, Yin Cui","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T00:20:55Z","title":"Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07074","kind":"arxiv","version":1},"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":"sha256:7a743e75de70f87039a8b2c5dec32596ccc97e2293c9815432495da8661e3a32","target":"record","created_at":"2026-07-05T03:40:20Z","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":"63bd291f7586ac522c336e3c99de9b7fde7a1ef7b8280b64904068991dcf8721","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T00:20:55Z","title_canon_sha256":"9058cc91ef1d319629353b97047175007ddc2d02115df2427f3840c6899e5be4"},"schema_version":"1.0","source":{"id":"2112.07074","kind":"arxiv","version":1}},"canonical_sha256":"0ac73d402b7cc035c88935c5f380416b65af785d972799d95c2dfcc28914b41d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ac73d402b7cc035c88935c5f380416b65af785d972799d95c2dfcc28914b41d","first_computed_at":"2026-07-05T03:40:20.608522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:20.608522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A6I2Y1NF9q4T3JBJ1A9E4SYbiOy0PkXZL9QoTlsUCxtwi+XnZj/Lfz0yWOYBsxtDvxsaMilzupCFvXfVa/AcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:20.608934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a743e75de70f87039a8b2c5dec32596ccc97e2293c9815432495da8661e3a32","sha256:1f2f0fbe644868a77a25465068d8eaf0eb945ef76d321ae1d01f88043c9a0624"],"state_sha256":"6ebe54306bfe3d3e52f2a06aa3bf7ed6ea7e5cb6c669f7ea74d29c40555c3a3e"}