{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HULR7H7H4VCLLB2IUOMA5CH6HG","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":"6c657dbf7e8aa3916074dcb28f9f3b9df078c325a63f5e6735ab9035a40e8953","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-03T12:50:26Z","title_canon_sha256":"9ecb727692ff79e1d9a3384680b384eb3d9170931131bddc485f35c7cf6bc562"},"schema_version":"1.0","source":{"id":"2106.01804","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01804","created_at":"2026-07-05T02:46:14Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01804v2","created_at":"2026-07-05T02:46:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01804","created_at":"2026-07-05T02:46:14Z"},{"alias_kind":"pith_short_12","alias_value":"HULR7H7H4VCL","created_at":"2026-07-05T02:46:14Z"},{"alias_kind":"pith_short_16","alias_value":"HULR7H7H4VCLLB2I","created_at":"2026-07-05T02:46:14Z"},{"alias_kind":"pith_short_8","alias_value":"HULR7H7H","created_at":"2026-07-05T02:46:14Z"}],"graph_snapshots":[{"event_id":"sha256:bf026219441e8c6cfc8d12e0749921eabc31422c04081bc4b5282c3246af5087","target":"graph","created_at":"2026-07-05T02:46:14Z","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/2106.01804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a pre-trained object detector to extract region-based visual features, then concatenates the image representation and text embedding as the input of Transformer to train. However, these methods face problems of using task-specific visual representation of the specific object detector for generic cross-modal understanding, and the computation inefficiency of two-","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Songfang Huang, Wenming Xiao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-03T12:50:26Z","title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01804","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":"sha256:30d52e6075dc2c083de89f78a0af527cd9fc7e9fd806f42d7a967635a061d1f3","target":"record","created_at":"2026-07-05T02:46:14Z","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":"6c657dbf7e8aa3916074dcb28f9f3b9df078c325a63f5e6735ab9035a40e8953","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-03T12:50:26Z","title_canon_sha256":"9ecb727692ff79e1d9a3384680b384eb3d9170931131bddc485f35c7cf6bc562"},"schema_version":"1.0","source":{"id":"2106.01804","kind":"arxiv","version":2}},"canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","first_computed_at":"2026-07-05T02:46:14.706884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:14.706884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H+C/DHR8TLfoV+8dnPqNiINoEZ5gToX/BFbB9BjM/YgO6yffo7C1vPONa26poaUK1cVV2er5j4IjAQCNLTl9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:14.707400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.01804","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30d52e6075dc2c083de89f78a0af527cd9fc7e9fd806f42d7a967635a061d1f3","sha256:bf026219441e8c6cfc8d12e0749921eabc31422c04081bc4b5282c3246af5087"],"state_sha256":"0d2e9ad20e297163adef9e1aa1220b33275752e79297d63906a9eaeec36fa36a"}