{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IFYXNABXZOKUIZ7UUG6K6Q2EHL","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":"df2615a6679935d39c488e41f28668a76968531ecc6c7a7515170daed123a321","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-15T08:37:55Z","title_canon_sha256":"e465683168c598de93fe615f1b6361a435aa572a9efbc9ca436843dced338923"},"schema_version":"1.0","source":{"id":"2101.06013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.06013","created_at":"2026-07-05T02:07:09Z"},{"alias_kind":"arxiv_version","alias_value":"2101.06013v1","created_at":"2026-07-05T02:07:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06013","created_at":"2026-07-05T02:07:09Z"},{"alias_kind":"pith_short_12","alias_value":"IFYXNABXZOKU","created_at":"2026-07-05T02:07:09Z"},{"alias_kind":"pith_short_16","alias_value":"IFYXNABXZOKUIZ7U","created_at":"2026-07-05T02:07:09Z"},{"alias_kind":"pith_short_8","alias_value":"IFYXNABX","created_at":"2026-07-05T02:07:09Z"}],"graph_snapshots":[{"event_id":"sha256:a4d2b183dcc61e6288966a4f320a6df60315a47537709afc2cfe2eb98aa469c9","target":"graph","created_at":"2026-07-05T02:07:09Z","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/2101.06013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The limits of applicability of vision-and-language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from task-specific datasets. This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We use an auxiliary training objective that encourages the learned representations to align with graph embeddings of matching entities in a KB. We empirically study the relevance of various KBs to multiple ta","authors_text":"Anthony Dick, Anton van den Hengel, Damien Teney, Violetta Shevchenko","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-15T08:37:55Z","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06013","kind":"arxiv","version":1},"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:e1abe76fc19485796ba581e3fa8b1381bf79d4477feb49d5e6ca0b4a50a486ce","target":"record","created_at":"2026-07-05T02:07:09Z","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":"df2615a6679935d39c488e41f28668a76968531ecc6c7a7515170daed123a321","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-15T08:37:55Z","title_canon_sha256":"e465683168c598de93fe615f1b6361a435aa572a9efbc9ca436843dced338923"},"schema_version":"1.0","source":{"id":"2101.06013","kind":"arxiv","version":1}},"canonical_sha256":"4171768037cb954467f4a1bcaf43443ad89e2510978dd464ebb85e474040bfb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4171768037cb954467f4a1bcaf43443ad89e2510978dd464ebb85e474040bfb6","first_computed_at":"2026-07-05T02:07:09.050650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:07:09.050650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qx+OMbwdl6d9pWRcHJZ0G7IFcvZsew8NA/Kw9+A2Wg8t5tMRYrMVVtkfyNr9cptHwzfbcEM+HM6zTuZijDI4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:07:09.051209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.06013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1abe76fc19485796ba581e3fa8b1381bf79d4477feb49d5e6ca0b4a50a486ce","sha256:a4d2b183dcc61e6288966a4f320a6df60315a47537709afc2cfe2eb98aa469c9"],"state_sha256":"4f1a1986408271f4c4c38607a53c5a53573c3ed32a06471b8354db3a078d9bf8"}