{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2H7KNHNLP3L5OGHTDESHCUCINR","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":"758578b3b09d683a7c701023bef9077adf86bac6f9245e0aa107274af0b4e4f4","cross_cats_sorted":["cs.CC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-20T11:27:21Z","title_canon_sha256":"c4377d6372b48c46b9a0fd9c066c16a56291f165f844fabe78bb3e740f986fcb"},"schema_version":"1.0","source":{"id":"2001.07059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.07059","created_at":"2026-07-05T00:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2001.07059v1","created_at":"2026-07-05T00:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07059","created_at":"2026-07-05T00:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"2H7KNHNLP3L5","created_at":"2026-07-05T00:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"2H7KNHNLP3L5OGHT","created_at":"2026-07-05T00:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"2H7KNHNL","created_at":"2026-07-05T00:34:27Z"}],"graph_snapshots":[{"event_id":"sha256:8ddad6d6df8258abadfc19fd1cc51972ba9d007ea6c2548a62755b7501c1d26e","target":"graph","created_at":"2026-07-05T00:34:27Z","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/2001.07059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) has emerged as a Visual Turing Test to validate the reasoning ability of AI agents. The pivot to existing VQA models is the joint embedding that is learned by combining the visual features from an image and the semantic features from a given question. Consequently, a large body of literature has focused on developing complex joint embedding strategies coupled with visual attention mechanisms to effectively capture the interplay between these two modalities. However, modelling the visual and semantic features in a high dimensional (joint embedding) space is compu","authors_text":"Moshiur R. Farazi, Nick Barnes, Salman H. Khan","cross_cats":["cs.CC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-20T11:27:21Z","title":"Accuracy vs. Complexity: A Trade-off in Visual Question Answering Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07059","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:b6300ff42eeda978b5f82a0418fbc26eea95f7b48b1fde6b2a04abd9b05e11a7","target":"record","created_at":"2026-07-05T00:34:27Z","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":"758578b3b09d683a7c701023bef9077adf86bac6f9245e0aa107274af0b4e4f4","cross_cats_sorted":["cs.CC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-20T11:27:21Z","title_canon_sha256":"c4377d6372b48c46b9a0fd9c066c16a56291f165f844fabe78bb3e740f986fcb"},"schema_version":"1.0","source":{"id":"2001.07059","kind":"arxiv","version":1}},"canonical_sha256":"d1fea69dab7ed7d718f319247150486c50cfc4fd09b63ffb0932043d8c4baa9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1fea69dab7ed7d718f319247150486c50cfc4fd09b63ffb0932043d8c4baa9c","first_computed_at":"2026-07-05T00:34:27.157206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:34:27.157206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U6jUKrzbk2ddCJrLjbstsFOEVnYSHnjqR5mM8zJ9VY8XrmjeJbDNoscj8iIv60iU2Y4uAhLyziMDOLaS6E3UDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:34:27.157617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.07059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6300ff42eeda978b5f82a0418fbc26eea95f7b48b1fde6b2a04abd9b05e11a7","sha256:8ddad6d6df8258abadfc19fd1cc51972ba9d007ea6c2548a62755b7501c1d26e"],"state_sha256":"507dacda87a53c85eac5e01fbd8c9c6e1ba3116db155272d07bf00e550980a81"}