{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AXOH6TUKP22USWREMO5INXL4BD","short_pith_number":"pith:AXOH6TUK","canonical_record":{"source":{"id":"2208.04060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T11:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"fe6bda2905bc10af0c6849929b32aaab600251f94d1d19fcad86973f601d2106","abstract_canon_sha256":"920e9974f7d95d78d5e7909f0d0a88397b9a45f2b1e208fa094e055674bb88f0"},"schema_version":"1.0"},"canonical_sha256":"05dc7f4e8a7eb5495a2463ba86dd7c08ca23ab0caa4583c8efb5ae0f432854ba","source":{"kind":"arxiv","id":"2208.04060","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04060","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04060v1","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04060","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"pith_short_12","alias_value":"AXOH6TUKP22U","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"pith_short_16","alias_value":"AXOH6TUKP22USWRE","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"pith_short_8","alias_value":"AXOH6TUK","created_at":"2026-07-05T04:46:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AXOH6TUKP22USWREMO5INXL4BD","target":"record","payload":{"canonical_record":{"source":{"id":"2208.04060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T11:15:45Z","cross_cats_sorted":[],"title_canon_sha256":"fe6bda2905bc10af0c6849929b32aaab600251f94d1d19fcad86973f601d2106","abstract_canon_sha256":"920e9974f7d95d78d5e7909f0d0a88397b9a45f2b1e208fa094e055674bb88f0"},"schema_version":"1.0"},"canonical_sha256":"05dc7f4e8a7eb5495a2463ba86dd7c08ca23ab0caa4583c8efb5ae0f432854ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:47.316409Z","signature_b64":"zj3t4a0/z9zx9cnglqQ4o1RTS1/0ixIdCbHZBeKTuHTLVgxp5kUNkcHABTLvqaKrTX8q6/hW1OWq0zuBTIYKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05dc7f4e8a7eb5495a2463ba86dd7c08ca23ab0caa4583c8efb5ae0f432854ba","last_reissued_at":"2026-07-05T04:46:47.315894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:47.315894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.04060","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":"2026-07-05T04:46:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MS0prU98X5o9zRqyKo1cj1KUfmo757qU+Zz1YiSFFA30fThUOwQES7tvshRFtFjFkd499GxyggBuuK5aMfP3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:51:49.816817Z"},"content_sha256":"f8c4f8146fbaf69e1430d33fb6266cacbfc56e395a0369ff87b9f5d897bc6476","schema_version":"1.0","event_id":"sha256:f8c4f8146fbaf69e1430d33fb6266cacbfc56e395a0369ff87b9f5d897bc6476"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AXOH6TUKP22USWREMO5INXL4BD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jaeseok Byun, Jianlong Fu, Taebaek Hwang, Taesup Moon","submitted_at":"2022-08-08T11:15:45Z","abstract_excerpt":"Most of the currently existing vision and language pre-training (VLP) methods have mainly focused on how to extract and align vision and text features. In contrast to the mainstream VLP methods, we highlight that two routinely applied steps during pre-training have crucial impact on the performance of the pre-trained model: in-batch hard negative sampling for image-text matching (ITM) and assigning the large masking probability for the masked language modeling (MLM). After empirically showing the unexpected effectiveness of above two steps, we systematically devise our GRIT-VLP, which adaptive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04060","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/2208.04060/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":"2026-07-05T04:46:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QSU9Xopnsh5wXM5XrcTceJ0uvMZ+OeIGl6aahgh+GccvyzOv4Fug93WA0rWcQGyEr07+bF2mvFAG41jEijb/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:51:49.817302Z"},"content_sha256":"0153d0bb7da8c9a932942369deb49a818c66cc1078649c6ddbd3816a8ea19a8a","schema_version":"1.0","event_id":"sha256:0153d0bb7da8c9a932942369deb49a818c66cc1078649c6ddbd3816a8ea19a8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AXOH6TUKP22USWREMO5INXL4BD/bundle.json","state_url":"https://pith.science/pith/AXOH6TUKP22USWREMO5INXL4BD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AXOH6TUKP22USWREMO5INXL4BD/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":"2026-08-04T21:51:49Z","links":{"resolver":"https://pith.science/pith/AXOH6TUKP22USWREMO5INXL4BD","bundle":"https://pith.science/pith/AXOH6TUKP22USWREMO5INXL4BD/bundle.json","state":"https://pith.science/pith/AXOH6TUKP22USWREMO5INXL4BD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AXOH6TUKP22USWREMO5INXL4BD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AXOH6TUKP22USWREMO5INXL4BD","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":"920e9974f7d95d78d5e7909f0d0a88397b9a45f2b1e208fa094e055674bb88f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T11:15:45Z","title_canon_sha256":"fe6bda2905bc10af0c6849929b32aaab600251f94d1d19fcad86973f601d2106"},"schema_version":"1.0","source":{"id":"2208.04060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04060","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04060v1","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04060","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"pith_short_12","alias_value":"AXOH6TUKP22U","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"pith_short_16","alias_value":"AXOH6TUKP22USWRE","created_at":"2026-07-05T04:46:47Z"},{"alias_kind":"pith_short_8","alias_value":"AXOH6TUK","created_at":"2026-07-05T04:46:47Z"}],"graph_snapshots":[{"event_id":"sha256:0153d0bb7da8c9a932942369deb49a818c66cc1078649c6ddbd3816a8ea19a8a","target":"graph","created_at":"2026-07-05T04:46:47Z","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/2208.04060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most of the currently existing vision and language pre-training (VLP) methods have mainly focused on how to extract and align vision and text features. In contrast to the mainstream VLP methods, we highlight that two routinely applied steps during pre-training have crucial impact on the performance of the pre-trained model: in-batch hard negative sampling for image-text matching (ITM) and assigning the large masking probability for the masked language modeling (MLM). After empirically showing the unexpected effectiveness of above two steps, we systematically devise our GRIT-VLP, which adaptive","authors_text":"Jaeseok Byun, Jianlong Fu, Taebaek Hwang, Taesup Moon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T11:15:45Z","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04060","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:f8c4f8146fbaf69e1430d33fb6266cacbfc56e395a0369ff87b9f5d897bc6476","target":"record","created_at":"2026-07-05T04:46:47Z","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":"920e9974f7d95d78d5e7909f0d0a88397b9a45f2b1e208fa094e055674bb88f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-08T11:15:45Z","title_canon_sha256":"fe6bda2905bc10af0c6849929b32aaab600251f94d1d19fcad86973f601d2106"},"schema_version":"1.0","source":{"id":"2208.04060","kind":"arxiv","version":1}},"canonical_sha256":"05dc7f4e8a7eb5495a2463ba86dd7c08ca23ab0caa4583c8efb5ae0f432854ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05dc7f4e8a7eb5495a2463ba86dd7c08ca23ab0caa4583c8efb5ae0f432854ba","first_computed_at":"2026-07-05T04:46:47.315894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:47.315894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zj3t4a0/z9zx9cnglqQ4o1RTS1/0ixIdCbHZBeKTuHTLVgxp5kUNkcHABTLvqaKrTX8q6/hW1OWq0zuBTIYKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:47.316409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.04060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8c4f8146fbaf69e1430d33fb6266cacbfc56e395a0369ff87b9f5d897bc6476","sha256:0153d0bb7da8c9a932942369deb49a818c66cc1078649c6ddbd3816a8ea19a8a"],"state_sha256":"f65420ab06eb1c8ae165caf51ee32af90ff7d16a27e5b6935fd538b657b961a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOptSvxjwswJBqhayHjUBJ1QqH3JCbZLpegFkPSfXf1Y5zpAlBzC004+hGF6b+f9DeGkHHZD4J2TPCrX4VS8Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:51:49.821275Z","bundle_sha256":"90af5b0aad822a6eca66deaee589f0e73abbd1dfe68610a2e1e588c6dbbc51f0"}}