{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BMA6D5WED5NPCFFWOQEZOIUQJD","short_pith_number":"pith:BMA6D5WE","schema_version":"1.0","canonical_sha256":"0b01e1f6c41f5af114b6740997229048c2992ebd7e20e5ad2e2cfe8e9ff989aa","source":{"kind":"arxiv","id":"2206.07643","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.07643","created_at":"2026-07-05T05:17:11.510994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07643v2","created_at":"2026-07-05T05:17:11.510994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07643","created_at":"2026-07-05T05:17:11.510994+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMA6D5WED5NP","created_at":"2026-07-05T05:17:11.510994+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMA6D5WED5NPCFFW","created_at":"2026-07-05T05:17:11.510994+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMA6D5WE","created_at":"2026-07-05T05:17:11.510994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14824","citing_title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD","json":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD.json","graph_json":"https://pith.science/api/pith-number/BMA6D5WED5NPCFFWOQEZOIUQJD/graph.json","events_json":"https://pith.science/api/pith-number/BMA6D5WED5NPCFFWOQEZOIUQJD/events.json","paper":"https://pith.science/paper/BMA6D5WE"},"agent_actions":{"view_html":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD","download_json":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD.json","view_paper":"https://pith.science/paper/BMA6D5WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07643&json=true","fetch_graph":"https://pith.science/api/pith-number/BMA6D5WED5NPCFFWOQEZOIUQJD/graph.json","fetch_events":"https://pith.science/api/pith-number/BMA6D5WED5NPCFFWOQEZOIUQJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/action/storage_attestation","attest_author":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/action/author_attestation","sign_citation":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/action/citation_signature","submit_replication":"https://pith.science/pith/BMA6D5WED5NPCFFWOQEZOIUQJD/action/replication_record"}},"created_at":"2026-07-05T05:17:11.510994+00:00","updated_at":"2026-07-05T05:17:11.510994+00:00"}