{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:D44FRNGV5LOV56CZYIE6L2EFNV","short_pith_number":"pith:D44FRNGV","schema_version":"1.0","canonical_sha256":"1f3858b4d5eadd5ef859c209e5e8856d668b982256c643886aa256f83b6d2954","source":{"kind":"arxiv","id":"2108.07073","version":1},"attestation_state":"computed","paper":{"title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunqi Wang, Ji Zhang, Jun Yu, Meng Wang, Yuhao Cui, Zhongzhou Zhao, Zhou Yu","submitted_at":"2021-08-16T13:16:58Z","abstract_excerpt":"Vision-and-language pretraining (VLP) aims to learn generic multimodal representations from massive image-text pairs. While various successful attempts have been proposed, learning fine-grained semantic alignments between image-text pairs plays a key role in their approaches. Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models. To this end, we introduce a new VLP method called ROSITA, which integrates the cross- and i"},"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":"2108.07073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-16T13:16:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"75918e50610827af74b73511d487b93a5ac6004baaa557ce24097e26af4d8052","abstract_canon_sha256":"457731406b0d20cbabad167fb0b44353d2d9214598faf8fba8fbeb8a792e7ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:00.743832Z","signature_b64":"rRErFMruB8U6GY2pCi/15/TTZieSdwEFRcWR1C4PJ0pYGTnXyOw3YRPB5K32wn71QHfCRTmURo9ApTziR6A0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f3858b4d5eadd5ef859c209e5e8856d668b982256c643886aa256f83b6d2954","last_reissued_at":"2026-07-05T03:06:00.743418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:00.743418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunqi Wang, Ji Zhang, Jun Yu, Meng Wang, Yuhao Cui, Zhongzhou Zhao, Zhou Yu","submitted_at":"2021-08-16T13:16:58Z","abstract_excerpt":"Vision-and-language pretraining (VLP) aims to learn generic multimodal representations from massive image-text pairs. While various successful attempts have been proposed, learning fine-grained semantic alignments between image-text pairs plays a key role in their approaches. Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models. To this end, we introduce a new VLP method called ROSITA, which integrates the cross- and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07073","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/2108.07073/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":"2108.07073","created_at":"2026-07-05T03:06:00.743473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07073v1","created_at":"2026-07-05T03:06:00.743473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07073","created_at":"2026-07-05T03:06:00.743473+00:00"},{"alias_kind":"pith_short_12","alias_value":"D44FRNGV5LOV","created_at":"2026-07-05T03:06:00.743473+00:00"},{"alias_kind":"pith_short_16","alias_value":"D44FRNGV5LOV56CZ","created_at":"2026-07-05T03:06:00.743473+00:00"},{"alias_kind":"pith_short_8","alias_value":"D44FRNGV","created_at":"2026-07-05T03:06:00.743473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV","json":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV.json","graph_json":"https://pith.science/api/pith-number/D44FRNGV5LOV56CZYIE6L2EFNV/graph.json","events_json":"https://pith.science/api/pith-number/D44FRNGV5LOV56CZYIE6L2EFNV/events.json","paper":"https://pith.science/paper/D44FRNGV"},"agent_actions":{"view_html":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV","download_json":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV.json","view_paper":"https://pith.science/paper/D44FRNGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07073&json=true","fetch_graph":"https://pith.science/api/pith-number/D44FRNGV5LOV56CZYIE6L2EFNV/graph.json","fetch_events":"https://pith.science/api/pith-number/D44FRNGV5LOV56CZYIE6L2EFNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV/action/storage_attestation","attest_author":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV/action/author_attestation","sign_citation":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV/action/citation_signature","submit_replication":"https://pith.science/pith/D44FRNGV5LOV56CZYIE6L2EFNV/action/replication_record"}},"created_at":"2026-07-05T03:06:00.743473+00:00","updated_at":"2026-07-05T03:06:00.743473+00:00"}