{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CX5GQIUIUGQL4AVU5HKMIYAWPM","short_pith_number":"pith:CX5GQIUI","canonical_record":{"source":{"id":"2007.13135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-26T14:26:18Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"f07f0ccb6b98ceacaa9993d8f6073a12bf7f6233758b16a779a92d20cc3cdc1c","abstract_canon_sha256":"0ed19fd5d82b00bd4cc23d0977d723e3acca305770427e004d7d03f77f6c1bf1"},"schema_version":"1.0"},"canonical_sha256":"15fa682288a1a0be02b4e9d4c460167b338593898996c92822ec557465a8b90d","source":{"kind":"arxiv","id":"2007.13135","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13135","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13135v1","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13135","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"CX5GQIUIUGQL","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"CX5GQIUIUGQL4AVU","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"CX5GQIUI","created_at":"2026-07-05T01:22:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CX5GQIUIUGQL4AVU5HKMIYAWPM","target":"record","payload":{"canonical_record":{"source":{"id":"2007.13135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-26T14:26:18Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"f07f0ccb6b98ceacaa9993d8f6073a12bf7f6233758b16a779a92d20cc3cdc1c","abstract_canon_sha256":"0ed19fd5d82b00bd4cc23d0977d723e3acca305770427e004d7d03f77f6c1bf1"},"schema_version":"1.0"},"canonical_sha256":"15fa682288a1a0be02b4e9d4c460167b338593898996c92822ec557465a8b90d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:07.010135Z","signature_b64":"9LVtRWtSgUY+HIPsEY0mE83ZNk9NOiJ5s/h2Iox0JF23fuSu6YUDbVwLyn2dICYZuOQoKBhMqQg/qq6L+eEjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15fa682288a1a0be02b4e9d4c460167b338593898996c92822ec557465a8b90d","last_reissued_at":"2026-07-05T01:22:07.009693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:07.009693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.13135","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uUky3j7klU2o5PxXh9oqbUhC8uiJykx4TA3zuC6EAu8LZYnDMNHS1DH8tW+u+K0efGyQ6ukCouqp9eq9+gbkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T20:06:30.379262Z"},"content_sha256":"e42a32c10e197d485730f00692d647567335a086ca0ae0798a06f7d55f26f486","schema_version":"1.0","event_id":"sha256:e42a32c10e197d485730f00692d647567335a086ca0ae0798a06f7d55f26f486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CX5GQIUIUGQL4AVU5HKMIYAWPM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Visual-Linguistic Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Gerard de Melo, Kai Shuang, Lei Shi, Peng Gao, Peng Su, Sen Su, Shijie Geng, Zhengkai Jiang, Zuohui Fu","submitted_at":"2020-07-26T14:26:18Z","abstract_excerpt":"Several multi-modality representation learning approaches such as LXMERT and ViLBERT have been proposed recently. Such approaches can achieve superior performance due to the high-level semantic information captured during large-scale multimodal pretraining. However, as ViLBERT and LXMERT adopt visual region regression and classification loss, they often suffer from domain gap and noisy label problems, based on the visual features having been pretrained on the Visual Genome dataset. To overcome these issues, we propose unbiased Contrastive Visual-Linguistic Pretraining (CVLP), which constructs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13135","kind":"arxiv","version":1},"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/2007.13135/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":"2026-07-05T01:22:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ET3bnORSDLPDO+BOdjEdjQnkQEUksSt7OV/FGKjiDFlLfIc53nR3xIkVp7Q69P+JLyRyN62CABW/bCltyOmbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T20:06:30.379645Z"},"content_sha256":"170324afedf846fe27aec5888b70c0ac49c20363aadbb82a3ed7673143e42e87","schema_version":"1.0","event_id":"sha256:170324afedf846fe27aec5888b70c0ac49c20363aadbb82a3ed7673143e42e87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM/bundle.json","state_url":"https://pith.science/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM/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":"2026-07-17T20:06:30Z","links":{"resolver":"https://pith.science/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM","bundle":"https://pith.science/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM/bundle.json","state":"https://pith.science/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CX5GQIUIUGQL4AVU5HKMIYAWPM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CX5GQIUIUGQL4AVU5HKMIYAWPM","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":"0ed19fd5d82b00bd4cc23d0977d723e3acca305770427e004d7d03f77f6c1bf1","cross_cats_sorted":["eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-26T14:26:18Z","title_canon_sha256":"f07f0ccb6b98ceacaa9993d8f6073a12bf7f6233758b16a779a92d20cc3cdc1c"},"schema_version":"1.0","source":{"id":"2007.13135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13135","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13135v1","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13135","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"pith_short_12","alias_value":"CX5GQIUIUGQL","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"pith_short_16","alias_value":"CX5GQIUIUGQL4AVU","created_at":"2026-07-05T01:22:07Z"},{"alias_kind":"pith_short_8","alias_value":"CX5GQIUI","created_at":"2026-07-05T01:22:07Z"}],"graph_snapshots":[{"event_id":"sha256:170324afedf846fe27aec5888b70c0ac49c20363aadbb82a3ed7673143e42e87","target":"graph","created_at":"2026-07-05T01:22:07Z","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/2007.13135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several multi-modality representation learning approaches such as LXMERT and ViLBERT have been proposed recently. Such approaches can achieve superior performance due to the high-level semantic information captured during large-scale multimodal pretraining. However, as ViLBERT and LXMERT adopt visual region regression and classification loss, they often suffer from domain gap and noisy label problems, based on the visual features having been pretrained on the Visual Genome dataset. To overcome these issues, we propose unbiased Contrastive Visual-Linguistic Pretraining (CVLP), which constructs ","authors_text":"Gerard de Melo, Kai Shuang, Lei Shi, Peng Gao, Peng Su, Sen Su, Shijie Geng, Zhengkai Jiang, Zuohui Fu","cross_cats":["eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-26T14:26:18Z","title":"Contrastive Visual-Linguistic Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13135","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:e42a32c10e197d485730f00692d647567335a086ca0ae0798a06f7d55f26f486","target":"record","created_at":"2026-07-05T01:22:07Z","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":"0ed19fd5d82b00bd4cc23d0977d723e3acca305770427e004d7d03f77f6c1bf1","cross_cats_sorted":["eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-26T14:26:18Z","title_canon_sha256":"f07f0ccb6b98ceacaa9993d8f6073a12bf7f6233758b16a779a92d20cc3cdc1c"},"schema_version":"1.0","source":{"id":"2007.13135","kind":"arxiv","version":1}},"canonical_sha256":"15fa682288a1a0be02b4e9d4c460167b338593898996c92822ec557465a8b90d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15fa682288a1a0be02b4e9d4c460167b338593898996c92822ec557465a8b90d","first_computed_at":"2026-07-05T01:22:07.009693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:22:07.009693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9LVtRWtSgUY+HIPsEY0mE83ZNk9NOiJ5s/h2Iox0JF23fuSu6YUDbVwLyn2dICYZuOQoKBhMqQg/qq6L+eEjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:22:07.010135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.13135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e42a32c10e197d485730f00692d647567335a086ca0ae0798a06f7d55f26f486","sha256:170324afedf846fe27aec5888b70c0ac49c20363aadbb82a3ed7673143e42e87"],"state_sha256":"ad08523b1ecdfa5905049c17eda32713728546670d079467089cc89aec1b6c14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vO0uu0oSU4+93LvsqhimLUk3VMhsVy8g8EuFz3scmlYpMV3k4dcd9Ds5/kc3Jq/elamQX5EJislKAaS5+q0nAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T20:06:30.381764Z","bundle_sha256":"43e0b64d9fb506f728c241547643d745070c71f852289447da9df2f09a417a1a"}}