{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OABC3WZHPPE4JSWEXCSA6NMVBV","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":"53a955a42c0eef8835e67a731826612701e7a7323c7c54713919c5d5a1318b73","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T01:49:58Z","title_canon_sha256":"a7a214f1eef58c064de546a264cac3f3af2300c7445c77d4a4c2651054a3d6f5"},"schema_version":"1.0","source":{"id":"2210.04135","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04135","created_at":"2026-07-05T07:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04135v3","created_at":"2026-07-05T07:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04135","created_at":"2026-07-05T07:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"OABC3WZHPPE4","created_at":"2026-07-05T07:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"OABC3WZHPPE4JSWE","created_at":"2026-07-05T07:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"OABC3WZH","created_at":"2026-07-05T07:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:34eb7301f1e1214ce7b36bad135b807ed871f1642429470662359cd618101660","target":"graph","created_at":"2026-07-05T07:06:20Z","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/2210.04135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hardik Shah, Jiachen Zhu, Li Jing, Rama Chellappa, Sayan Nag, Shraman Pramanick, Yann LeCun","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T01:49:58Z","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04135","kind":"arxiv","version":3},"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":"sha256:716b09ccf02c3ff811558b89683ce4172bbc0cb4fc372c8cf777f245c602a2d1","target":"record","created_at":"2026-07-05T07:06:20Z","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":"53a955a42c0eef8835e67a731826612701e7a7323c7c54713919c5d5a1318b73","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T01:49:58Z","title_canon_sha256":"a7a214f1eef58c064de546a264cac3f3af2300c7445c77d4a4c2651054a3d6f5"},"schema_version":"1.0","source":{"id":"2210.04135","kind":"arxiv","version":3}},"canonical_sha256":"70022ddb277bc9c4cac4b8a40f35950d5c270dd7c29d1ec424693da2c0ca3db2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70022ddb277bc9c4cac4b8a40f35950d5c270dd7c29d1ec424693da2c0ca3db2","first_computed_at":"2026-07-05T07:06:20.551919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:20.551919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MtVQft13Bi3wQ38DW/ea2FYGpOxNFlkQDEGBKwSfuZKCdZ24qTsQwl8fOmXTF2W/dMl5IKhzkThadA2ROJ+RDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:20.552310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04135","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:716b09ccf02c3ff811558b89683ce4172bbc0cb4fc372c8cf777f245c602a2d1","sha256:34eb7301f1e1214ce7b36bad135b807ed871f1642429470662359cd618101660"],"state_sha256":"b04e2f76cc284dcaf7e868db31c305c4ac5bdffecb4276ab12496cd3d42c9356"}