{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OABC3WZHPPE4JSWEXCSA6NMVBV","short_pith_number":"pith:OABC3WZH","schema_version":"1.0","canonical_sha256":"70022ddb277bc9c4cac4b8a40f35950d5c270dd7c29d1ec424693da2c0ca3db2","source":{"kind":"arxiv","id":"2210.04135","version":3},"attestation_state":"computed","paper":{"title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hardik Shah, Jiachen Zhu, Li Jing, Rama Chellappa, Sayan Nag, Shraman Pramanick, Yann LeCun","submitted_at":"2022-10-09T01:49:58Z","abstract_excerpt":"Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on fine-grained region-level tasks, such as object detection, segmentation, and referring expression comprehension. Unfortunately, such high-resolution images with accurate bounding box annotations are expensive to collect and use for supervision at scale. In this work, we propose VoLTA (Vision-Language Transformer with weakly-supervised local-feature Alignment), a "},"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":"2210.04135","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T01:49:58Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"a7a214f1eef58c064de546a264cac3f3af2300c7445c77d4a4c2651054a3d6f5","abstract_canon_sha256":"53a955a42c0eef8835e67a731826612701e7a7323c7c54713919c5d5a1318b73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:20.552310Z","signature_b64":"MtVQft13Bi3wQ38DW/ea2FYGpOxNFlkQDEGBKwSfuZKCdZ24qTsQwl8fOmXTF2W/dMl5IKhzkThadA2ROJ+RDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70022ddb277bc9c4cac4b8a40f35950d5c270dd7c29d1ec424693da2c0ca3db2","last_reissued_at":"2026-07-05T07:06:20.551919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:20.551919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hardik Shah, Jiachen Zhu, Li Jing, Rama Chellappa, Sayan Nag, Shraman Pramanick, Yann LeCun","submitted_at":"2022-10-09T01:49:58Z","abstract_excerpt":"Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on fine-grained region-level tasks, such as object detection, segmentation, and referring expression comprehension. Unfortunately, such high-resolution images with accurate bounding box annotations are expensive to collect and use for supervision at scale. In this work, we propose VoLTA (Vision-Language Transformer with weakly-supervised local-feature Alignment), a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04135","kind":"arxiv","version":3},"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/2210.04135/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":"2210.04135","created_at":"2026-07-05T07:06:20.551969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04135v3","created_at":"2026-07-05T07:06:20.551969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04135","created_at":"2026-07-05T07:06:20.551969+00:00"},{"alias_kind":"pith_short_12","alias_value":"OABC3WZHPPE4","created_at":"2026-07-05T07:06:20.551969+00:00"},{"alias_kind":"pith_short_16","alias_value":"OABC3WZHPPE4JSWE","created_at":"2026-07-05T07:06:20.551969+00:00"},{"alias_kind":"pith_short_8","alias_value":"OABC3WZH","created_at":"2026-07-05T07:06:20.551969+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/OABC3WZHPPE4JSWEXCSA6NMVBV","json":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV.json","graph_json":"https://pith.science/api/pith-number/OABC3WZHPPE4JSWEXCSA6NMVBV/graph.json","events_json":"https://pith.science/api/pith-number/OABC3WZHPPE4JSWEXCSA6NMVBV/events.json","paper":"https://pith.science/paper/OABC3WZH"},"agent_actions":{"view_html":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV","download_json":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV.json","view_paper":"https://pith.science/paper/OABC3WZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04135&json=true","fetch_graph":"https://pith.science/api/pith-number/OABC3WZHPPE4JSWEXCSA6NMVBV/graph.json","fetch_events":"https://pith.science/api/pith-number/OABC3WZHPPE4JSWEXCSA6NMVBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV/action/storage_attestation","attest_author":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV/action/author_attestation","sign_citation":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV/action/citation_signature","submit_replication":"https://pith.science/pith/OABC3WZHPPE4JSWEXCSA6NMVBV/action/replication_record"}},"created_at":"2026-07-05T07:06:20.551969+00:00","updated_at":"2026-07-05T07:06:20.551969+00:00"}