{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CYDYX5C6FNVIT4PQ6QWXPOXMHG","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":"22fa01afc2b2fe34a118155314b56fd05bed079f22d987c4700b5d8241057ae6","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-02T07:39:28Z","title_canon_sha256":"e4260a4d4063220719c375b818c04e0c9b98c1a5c232637dcc206a36d34186b4"},"schema_version":"1.0","source":{"id":"2004.00849","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00849","created_at":"2026-07-05T01:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00849v2","created_at":"2026-07-05T01:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00849","created_at":"2026-07-05T01:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"CYDYX5C6FNVI","created_at":"2026-07-05T01:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"CYDYX5C6FNVIT4PQ","created_at":"2026-07-05T01:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"CYDYX5C6","created_at":"2026-07-05T01:11:46Z"}],"graph_snapshots":[{"event_id":"sha256:814b8de1ee3e5a3f47c1d86316fb974d2fe0fd6d6374742c9df941a36a228eb7","target":"graph","created_at":"2026-07-05T01:11:46Z","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/2004.00849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image pixels and language semantics directly from image and sentence pairs instead of using region-based image features as the most recent vision and language tasks. Our Pixel-BERT which aligns semantic connection in pixel and text level solves the limitation of task-specific visual representation for vision and language tasks. It also relieves the cost of boundi","authors_text":"Bei Liu, Dongmei Fu, Jianlong Fu, Zhaoyang Zeng, Zhicheng Huang","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-02T07:39:28Z","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00849","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":"sha256:952fbbb6a0590af12a93519769197d239a3e6d2290967b9b51c99b01605f5d2f","target":"record","created_at":"2026-07-05T01:11:46Z","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":"22fa01afc2b2fe34a118155314b56fd05bed079f22d987c4700b5d8241057ae6","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-02T07:39:28Z","title_canon_sha256":"e4260a4d4063220719c375b818c04e0c9b98c1a5c232637dcc206a36d34186b4"},"schema_version":"1.0","source":{"id":"2004.00849","kind":"arxiv","version":2}},"canonical_sha256":"16078bf45e2b6a89f1f0f42d77baec3998f14e4f38ce3539b9328d50ac4e8341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16078bf45e2b6a89f1f0f42d77baec3998f14e4f38ce3539b9328d50ac4e8341","first_computed_at":"2026-07-05T01:11:46.416533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:46.416533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zdNmIeklJ3WvNDklPycxcwSbrx69hjzv+Vxtmow/NLcbDWthpIA05SO97wLbtLffmsWS/BOoYqWLtVbJjnyfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:46.416934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.00849","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:952fbbb6a0590af12a93519769197d239a3e6d2290967b9b51c99b01605f5d2f","sha256:814b8de1ee3e5a3f47c1d86316fb974d2fe0fd6d6374742c9df941a36a228eb7"],"state_sha256":"4ba5008dc1a5ad8843c42f7899a761b4a27e7d7c91a32e04a9e52931e3bf3e8a"}