{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HULR7H7H4VCLLB2IUOMA5CH6HG","short_pith_number":"pith:HULR7H7H","canonical_record":{"source":{"id":"2106.01804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-03T12:50:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9ecb727692ff79e1d9a3384680b384eb3d9170931131bddc485f35c7cf6bc562","abstract_canon_sha256":"6c657dbf7e8aa3916074dcb28f9f3b9df078c325a63f5e6735ab9035a40e8953"},"schema_version":"1.0"},"canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","source":{"kind":"arxiv","id":"2106.01804","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HULR7H7H4VCLLB2IUOMA5CH6HG","target":"record","payload":{"canonical_record":{"source":{"id":"2106.01804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-03T12:50:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"9ecb727692ff79e1d9a3384680b384eb3d9170931131bddc485f35c7cf6bc562","abstract_canon_sha256":"6c657dbf7e8aa3916074dcb28f9f3b9df078c325a63f5e6735ab9035a40e8953"},"schema_version":"1.0"},"canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:14.707400Z","signature_b64":"H+C/DHR8TLfoV+8dnPqNiINoEZ5gToX/BFbB9BjM/YgO6yffo7C1vPONa26poaUK1cVV2er5j4IjAQCNLTl9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d171f9fe7e544b58748a3980e88fe399832f5b243978fbe7faa08fc590e7f98","last_reissued_at":"2026-07-05T02:46:14.706884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:14.706884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.01804","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:46:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9/CgND6cwFSHwmcJT9TCXwpiTIth5gduHp1qm2oLEeYwgUNXI4yNEWdF0EWFtZcNbmLAx2afAUF59+TDjL8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T08:58:39.355923Z"},"content_sha256":"30d52e6075dc2c083de89f78a0af527cd9fc7e9fd806f42d7a967635a061d1f3","schema_version":"1.0","event_id":"sha256:30d52e6075dc2c083de89f78a0af527cd9fc7e9fd806f42d7a967635a061d1f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HULR7H7H4VCLLB2IUOMA5CH6HG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Haiyang Xu, Ming Yan, Songfang Huang, Wenming Xiao","submitted_at":"2021-06-03T12:50:26Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01804","kind":"arxiv","version":2},"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/2106.01804/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":"2026-07-05T02:46:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0xjQKn00ozrKAoAgNiwq3Q4oJdoD5wnSLY7skWi3ofVCcRHSzgdM/VY8xTRlOSIZ6lVz+7FJiuuht0IUmH5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T08:58:39.356301Z"},"content_sha256":"bf026219441e8c6cfc8d12e0749921eabc31422c04081bc4b5282c3246af5087","schema_version":"1.0","event_id":"sha256:bf026219441e8c6cfc8d12e0749921eabc31422c04081bc4b5282c3246af5087"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/bundle.json","state_url":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/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":"2026-07-19T08:58:39Z","links":{"resolver":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG","bundle":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/bundle.json","state":"https://pith.science/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HULR7H7H4VCLLB2IUOMA5CH6HG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"42EARUqVVtfSJ8QrxxypEX0est5H970dBzTfrt35KbFYVIF5JCsMRdBx7gESMmRqf8y2/IMqX8LuV41pVtgZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T08:58:39.358385Z","bundle_sha256":"2f8d10d7280891f243a10790c56adaf6e886a984bbc73fe480aca9157dc7661e"}}