{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BMA6D5WED5NPCFFWOQEZOIUQJD","short_pith_number":"pith:BMA6D5WE","canonical_record":{"source":{"id":"2206.07643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T16:41:29Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"94428f44060b7486ecee5fee0d0a7b0b629c488c04ada35b46ca972952c6fda3","abstract_canon_sha256":"cf5cf7ba2bb173effbce57230d77b6fd9a6e2fe0b3425644309a203100259856"},"schema_version":"1.0"},"canonical_sha256":"0b01e1f6c41f5af114b6740997229048c2992ebd7e20e5ad2e2cfe8e9ff989aa","source":{"kind":"arxiv","id":"2206.07643","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07643","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07643v2","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07643","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"BMA6D5WED5NP","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"BMA6D5WED5NPCFFW","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"BMA6D5WE","created_at":"2026-07-05T05:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BMA6D5WED5NPCFFWOQEZOIUQJD","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T16:41:29Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"94428f44060b7486ecee5fee0d0a7b0b629c488c04ada35b46ca972952c6fda3","abstract_canon_sha256":"cf5cf7ba2bb173effbce57230d77b6fd9a6e2fe0b3425644309a203100259856"},"schema_version":"1.0"},"canonical_sha256":"0b01e1f6c41f5af114b6740997229048c2992ebd7e20e5ad2e2cfe8e9ff989aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:11.511374Z","signature_b64":"QFdgniF7QCr5NuZ7eXuLNXJAYOb3z8HKaouaLsCqg+Sro1bcOcOvdrMKGDaZ2OwnPxZ0P0YRSSYvOlU4HUeMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b01e1f6c41f5af114b6740997229048c2992ebd7e20e5ad2e2cfe8e9ff989aa","last_reissued_at":"2026-07-05T05:17:11.510937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:11.510937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07643","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":"2026-07-05T05:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zzupfsy81lm7ryhnBq8H6hPuHU9/mEV/umchZnUXofk28hpwnbII6CMAJhk8pMT3GE3cnJ6NkgmN5JVwWB78DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:36:04.039570Z"},"content_sha256":"5e6a3b5fef7066e332b14e4b485d2004beddc4339b5c659daa2fef7238b146a9","schema_version":"1.0","event_id":"sha256:5e6a3b5fef7066e332b14e4b485d2004beddc4339b5c659daa2fef7238b146a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BMA6D5WED5NPCFFWOQEZOIUQJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aishwarya Kamath, Ce Liu, Jianfeng Gao, Jianfeng Wang, Lijuan Wang, Linjie Li, Nanyun Peng, Pengchuan Zhang, Yann LeCun, Zhe Gan, Zicheng Liu, Zi-Yi Dou","submitted_at":"2022-06-15T16:41:29Z","abstract_excerpt":"Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07643","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/2206.07643/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":"2026-07-05T05:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jh0ULhr3dWsdbJKW5hMvmiYo/a6kJkhNFYLLOMkq6m43WlESIyx13uVPmTHYzNAN/hELNUs+Ky9SDTPT38lxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:36:04.040093Z"},"content_sha256":"ec0cff198c749abf7d9249ba8731b2c9c91789f801cb5773634a61f94f0c609d","schema_version":"1.0","event_id":"sha256:ec0cff198c749abf7d9249ba8731b2c9c91789f801cb5773634a61f94f0c609d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/bundle.json","state_url":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/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":"2026-08-06T00:36:04Z","links":{"resolver":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD","bundle":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/bundle.json","state":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BMA6D5WED5NPCFFWOQEZOIUQJD","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":"cf5cf7ba2bb173effbce57230d77b6fd9a6e2fe0b3425644309a203100259856","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T16:41:29Z","title_canon_sha256":"94428f44060b7486ecee5fee0d0a7b0b629c488c04ada35b46ca972952c6fda3"},"schema_version":"1.0","source":{"id":"2206.07643","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07643","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07643v2","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07643","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"BMA6D5WED5NP","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"BMA6D5WED5NPCFFW","created_at":"2026-07-05T05:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"BMA6D5WE","created_at":"2026-07-05T05:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:ec0cff198c749abf7d9249ba8731b2c9c91789f801cb5773634a61f94f0c609d","target":"graph","created_at":"2026-07-05T05:17:11Z","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/2206.07643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusio","authors_text":"Aishwarya Kamath, Ce Liu, Jianfeng Gao, Jianfeng Wang, Lijuan Wang, Linjie Li, Nanyun Peng, Pengchuan Zhang, Yann LeCun, Zhe Gan, Zicheng Liu, Zi-Yi Dou","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T16:41:29Z","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07643","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":"sha256:5e6a3b5fef7066e332b14e4b485d2004beddc4339b5c659daa2fef7238b146a9","target":"record","created_at":"2026-07-05T05:17:11Z","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":"cf5cf7ba2bb173effbce57230d77b6fd9a6e2fe0b3425644309a203100259856","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T16:41:29Z","title_canon_sha256":"94428f44060b7486ecee5fee0d0a7b0b629c488c04ada35b46ca972952c6fda3"},"schema_version":"1.0","source":{"id":"2206.07643","kind":"arxiv","version":2}},"canonical_sha256":"0b01e1f6c41f5af114b6740997229048c2992ebd7e20e5ad2e2cfe8e9ff989aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b01e1f6c41f5af114b6740997229048c2992ebd7e20e5ad2e2cfe8e9ff989aa","first_computed_at":"2026-07-05T05:17:11.510937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:11.510937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QFdgniF7QCr5NuZ7eXuLNXJAYOb3z8HKaouaLsCqg+Sro1bcOcOvdrMKGDaZ2OwnPxZ0P0YRSSYvOlU4HUeMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:11.511374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07643","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e6a3b5fef7066e332b14e4b485d2004beddc4339b5c659daa2fef7238b146a9","sha256:ec0cff198c749abf7d9249ba8731b2c9c91789f801cb5773634a61f94f0c609d"],"state_sha256":"0aaa78e267850724f350d8845593825cdd307b73e39734324679478e2c1e77a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YqwhuO2IeOLNgd/2W8I6pT1qB3hMSSzWf03ZmFpZwMjizWQYEZFnIIJOirQuEQD7c709wPVpgU7POvX+OmhlBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:36:04.048197Z","bundle_sha256":"2ae01f959cf19f230ea4a3e58ad9c1651984df1e4805b93869c1eae2edd47c7d"}}