{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4EP6S2PSEJU2LMEMBNI3MOH6XG","short_pith_number":"pith:4EP6S2PS","canonical_record":{"source":{"id":"2104.00107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T20:47:32Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d8e71410bc2fa4c788b738992329b54d315c8a4651a80d0d667bd1fe14312e32","abstract_canon_sha256":"785a5e4769acb7d44b9a927a01a68d94af1ec3c43eac74491f0a93960071d2eb"},"schema_version":"1.0"},"canonical_sha256":"e11fe969f22269a5b08c0b51b638feb99f90d9a005327ea736014b4cb491cf9a","source":{"kind":"arxiv","id":"2104.00107","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4EP6S2PSEJU2LMEMBNI3MOH6XG","target":"record","payload":{"canonical_record":{"source":{"id":"2104.00107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T20:47:32Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d8e71410bc2fa4c788b738992329b54d315c8a4651a80d0d667bd1fe14312e32","abstract_canon_sha256":"785a5e4769acb7d44b9a927a01a68d94af1ec3c43eac74491f0a93960071d2eb"},"schema_version":"1.0"},"canonical_sha256":"e11fe969f22269a5b08c0b51b638feb99f90d9a005327ea736014b4cb491cf9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:23.933684Z","signature_b64":"HMK+ykEySGCJHjn1qJnjQRhQE7zbVWqA91X27L58fQf2qVCtCy9IjEo6s2QMFPqViPEiTHLArZzaivBdMRL6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11fe969f22269a5b08c0b51b638feb99f90d9a005327ea736014b4cb491cf9a","last_reissued_at":"2026-07-05T02:28:23.933230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:23.933230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.00107","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:28:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZ3wxkr/++5g1e1FfMv/zXmsnVKEUN0IF7Vb0oPSGShPJQKCqUFsDwS6J7EbJcvmK6VkjdzjSumom8aqMECaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:24:58.906692Z"},"content_sha256":"fb9bd7db5adf4c92471ae92040cc5947a2fb9943eb5618cbc42ab64efedac50d","schema_version":"1.0","event_id":"sha256:fb9bd7db5adf4c92471ae92040cc5947a2fb9943eb5618cbc42ab64efedac50d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4EP6S2PSEJU2LMEMBNI3MOH6XG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysis on Image Set Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Khattar, Aviral Joshi, Har Simrat Singh, Pulkit Goel, Rohit Prakash Barnwal","submitted_at":"2021-03-31T20:47:32Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00107","kind":"arxiv","version":1},"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/2104.00107/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":"2026-07-05T02:28:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZq9akWXzOv6JuW4rHvrNHrl24/sF6LkQP6/Jo7JAFDZWuh5lK5wvEnN8SNpbpLtqpsaXROoeroc1Ji/5pjyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:24:58.907241Z"},"content_sha256":"99b57d38755a26816d8cfd337e4416b1de93f6c504426abb65b97c0912e74a45","schema_version":"1.0","event_id":"sha256:99b57d38755a26816d8cfd337e4416b1de93f6c504426abb65b97c0912e74a45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG/bundle.json","state_url":"https://pith.science/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG/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":"2026-08-15T23:24:58Z","links":{"resolver":"https://pith.science/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG","bundle":"https://pith.science/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG/bundle.json","state":"https://pith.science/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EP6S2PSEJU2LMEMBNI3MOH6XG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r4mDX+fsia36qmHax+kK72L9gUtAVx54y4FDfCgiNDyRIhHI9esJl2xr0SmMhdgEQeaQFKrjRJ9hzhMKw5oUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:24:58.910701Z","bundle_sha256":"6b8d6f104c9b93997131226e47122b585a2eb7d7b52edc6624b77dd679f5e9e9"}}