{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZDNM2VJRVSHPZGR7NULDAUPUUR","short_pith_number":"pith:ZDNM2VJR","canonical_record":{"source":{"id":"2109.10504","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T03:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"3a4477bc1901a4d6034a409c57e59e8baa2a4fb829a58252f51d3f213e1b7873","abstract_canon_sha256":"7d23647212d9678a96ff3bb47543e44042840893012571cd0dcda89b7810a3e6"},"schema_version":"1.0"},"canonical_sha256":"c8dacd5531ac8efc9a3f6d163051f4a45e8a1987cd9606c186c528299a2a3651","source":{"kind":"arxiv","id":"2109.10504","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZDNM2VJRVSHPZGR7NULDAUPUUR","target":"record","payload":{"canonical_record":{"source":{"id":"2109.10504","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-22T03:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"3a4477bc1901a4d6034a409c57e59e8baa2a4fb829a58252f51d3f213e1b7873","abstract_canon_sha256":"7d23647212d9678a96ff3bb47543e44042840893012571cd0dcda89b7810a3e6"},"schema_version":"1.0"},"canonical_sha256":"c8dacd5531ac8efc9a3f6d163051f4a45e8a1987cd9606c186c528299a2a3651","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:32.823427Z","signature_b64":"Kd9tl74lXQUmEYIBc53pxc7fynSZyMuRJKO4wze2BuzuoBVJNh409pLe9Y1nGU3XnfTYUBkmdanDcRMR+q2XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8dacd5531ac8efc9a3f6d163051f4a45e8a1987cd9606c186c528299a2a3651","last_reissued_at":"2026-07-05T04:46:32.822994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:32.822994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.10504","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2XasqVYgvSiG/SefoqEwdHzzNjl3bX3KQCFuKN03NyO36vxd+8Vbt5sKXmH5c1jrNbrfhoNZ+mq0UcNEF4gDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:48:57.198325Z"},"content_sha256":"9f53f45c4122033ac91e0faf5bf13f42bff0fbdeb9fbfb0a2a89a2ad30f49776","schema_version":"1.0","event_id":"sha256:9f53f45c4122033ac91e0faf5bf13f42bff0fbdeb9fbfb0a2a89a2ad30f49776"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZDNM2VJRVSHPZGR7NULDAUPUUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Nan Duan, Shao-Yen Tseng, Vasudev Lal, Xuming He, Yongfei Liu","submitted_at":"2021-09-22T03:38:05Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10504","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/2109.10504/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JHOcO6vKf1C3qW0R38r3XzvV6e0k7YJGngUk6jERCkjaDH8wwl2oxjck+otgzVX9esfiqIU9nj3vehvFi2pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:48:57.198706Z"},"content_sha256":"582f2b4902bee18d7b5ee52f2c3b8221d93cac820dc15e80e093127f1810fb0a","schema_version":"1.0","event_id":"sha256:582f2b4902bee18d7b5ee52f2c3b8221d93cac820dc15e80e093127f1810fb0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR/bundle.json","state_url":"https://pith.science/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T07:48:57Z","links":{"resolver":"https://pith.science/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR","bundle":"https://pith.science/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR/bundle.json","state":"https://pith.science/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDNM2VJRVSHPZGR7NULDAUPUUR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bc541bGlWddix8yIoRU6KIFkGsj0e+xDXRdEIE4JfabqHKjVFqE0bSEZQOa3BKc+UbsmXZi8P/AxwIagA2tsBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:48:57.200792Z","bundle_sha256":"d0abebc058e51f4fe5f77fc02ebead5b8a6df3d92abac269d05b64d2a109fd33"}}