{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4EP6S2PSEJU2LMEMBNI3MOH6XG","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":"785a5e4769acb7d44b9a927a01a68d94af1ec3c43eac74491f0a93960071d2eb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T20:47:32Z","title_canon_sha256":"d8e71410bc2fa4c788b738992329b54d315c8a4651a80d0d667bd1fe14312e32"},"schema_version":"1.0","source":{"id":"2104.00107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00107","created_at":"2026-07-05T02:28:23Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00107v1","created_at":"2026-07-05T02:28:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00107","created_at":"2026-07-05T02:28:23Z"},{"alias_kind":"pith_short_12","alias_value":"4EP6S2PSEJU2","created_at":"2026-07-05T02:28:23Z"},{"alias_kind":"pith_short_16","alias_value":"4EP6S2PSEJU2LMEM","created_at":"2026-07-05T02:28:23Z"},{"alias_kind":"pith_short_8","alias_value":"4EP6S2PS","created_at":"2026-07-05T02:28:23Z"}],"graph_snapshots":[{"event_id":"sha256:99b57d38755a26816d8cfd337e4416b1de93f6c504426abb65b97c0912e74a45","target":"graph","created_at":"2026-07-05T02:28:23Z","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/2104.00107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the challenge of Visual Question Answering in multi-image setting for the ISVQA dataset. Traditional VQA tasks have focused on a single-image setting where the target answer is generated from a single image. Image set VQA, however, comprises of a set of images and requires finding connection between images, relate the objects across images based on these connections and generate a unified answer. In this report, we work with 4 approaches in a bid to improve the performance on the task. We analyse and compare our results with three baseline models - LXMERT, HME-VideoQA and VisualBERT ","authors_text":"Abhinav Khattar, Aviral Joshi, Har Simrat Singh, Pulkit Goel, Rohit Prakash Barnwal","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T20:47:32Z","title":"Analysis on Image Set Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00107","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:fb9bd7db5adf4c92471ae92040cc5947a2fb9943eb5618cbc42ab64efedac50d","target":"record","created_at":"2026-07-05T02:28:23Z","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":"785a5e4769acb7d44b9a927a01a68d94af1ec3c43eac74491f0a93960071d2eb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T20:47:32Z","title_canon_sha256":"d8e71410bc2fa4c788b738992329b54d315c8a4651a80d0d667bd1fe14312e32"},"schema_version":"1.0","source":{"id":"2104.00107","kind":"arxiv","version":1}},"canonical_sha256":"e11fe969f22269a5b08c0b51b638feb99f90d9a005327ea736014b4cb491cf9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e11fe969f22269a5b08c0b51b638feb99f90d9a005327ea736014b4cb491cf9a","first_computed_at":"2026-07-05T02:28:23.933230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:23.933230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HMK+ykEySGCJHjn1qJnjQRhQE7zbVWqA91X27L58fQf2qVCtCy9IjEo6s2QMFPqViPEiTHLArZzaivBdMRL6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:23.933684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb9bd7db5adf4c92471ae92040cc5947a2fb9943eb5618cbc42ab64efedac50d","sha256:99b57d38755a26816d8cfd337e4416b1de93f6c504426abb65b97c0912e74a45"],"state_sha256":"132b8fdfed93a6e82b2fc56ad69516d4e1ca8187e47a6985fb47285fdc7c944a"}