{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZDNM2VJRVSHPZGR7NULDAUPUUR","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":"7d23647212d9678a96ff3bb47543e44042840893012571cd0dcda89b7810a3e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T03:38:05Z","title_canon_sha256":"3a4477bc1901a4d6034a409c57e59e8baa2a4fb829a58252f51d3f213e1b7873"},"schema_version":"1.0","source":{"id":"2109.10504","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10504","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10504v3","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10504","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZDNM2VJRVSHP","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZDNM2VJRVSHPZGR7","created_at":"2026-07-05T04:46:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZDNM2VJR","created_at":"2026-07-05T04:46:32Z"}],"graph_snapshots":[{"event_id":"sha256:582f2b4902bee18d7b5ee52f2c3b8221d93cac820dc15e80e093127f1810fb0a","target":"graph","created_at":"2026-07-05T04:46:32Z","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/2109.10504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning. Previous mainstream VLP approaches typically adopt a two-step strategy relying on external object detectors to encode images in a multi-modal Transformer framework, which suffer from restrictive object concept space, limited image context and inefficient computation. In this paper, we propose an object-aware end-to-end VLP framework, which directly feeds image ","authors_text":"Chenfei Wu, Nan Duan, Shao-Yen Tseng, Vasudev Lal, Xuming He, Yongfei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T03:38:05Z","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10504","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":"sha256:9f53f45c4122033ac91e0faf5bf13f42bff0fbdeb9fbfb0a2a89a2ad30f49776","target":"record","created_at":"2026-07-05T04:46:32Z","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":"7d23647212d9678a96ff3bb47543e44042840893012571cd0dcda89b7810a3e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T03:38:05Z","title_canon_sha256":"3a4477bc1901a4d6034a409c57e59e8baa2a4fb829a58252f51d3f213e1b7873"},"schema_version":"1.0","source":{"id":"2109.10504","kind":"arxiv","version":3}},"canonical_sha256":"c8dacd5531ac8efc9a3f6d163051f4a45e8a1987cd9606c186c528299a2a3651","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8dacd5531ac8efc9a3f6d163051f4a45e8a1987cd9606c186c528299a2a3651","first_computed_at":"2026-07-05T04:46:32.822994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:32.822994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kd9tl74lXQUmEYIBc53pxc7fynSZyMuRJKO4wze2BuzuoBVJNh409pLe9Y1nGU3XnfTYUBkmdanDcRMR+q2XCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:32.823427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10504","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f53f45c4122033ac91e0faf5bf13f42bff0fbdeb9fbfb0a2a89a2ad30f49776","sha256:582f2b4902bee18d7b5ee52f2c3b8221d93cac820dc15e80e093127f1810fb0a"],"state_sha256":"520cb395a5e513ceb7ccc083fca7a70583fb187e3034684c445e6e81ffb9cab1"}