{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TUAZKOL24XB6QWE2SV6QP44UUC","short_pith_number":"pith:TUAZKOL2","canonical_record":{"source":{"id":"2112.13706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T14:28:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"16e08fc24dc60af0ff6c1e1ceff176b095a5f00443435be64a78e8b2216012ac","abstract_canon_sha256":"4165159f732f27635973a743826d3f60d73c2b6eb8db93296e4f5f2faffdee9f"},"schema_version":"1.0"},"canonical_sha256":"9d0195397ae5c3e8589a957d07f394a08c79a45b55ad99e01145aaecf8cf1346","source":{"kind":"arxiv","id":"2112.13706","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13706","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13706v2","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13706","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"pith_short_12","alias_value":"TUAZKOL24XB6","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"pith_short_16","alias_value":"TUAZKOL24XB6QWE2","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"pith_short_8","alias_value":"TUAZKOL2","created_at":"2026-07-05T03:54:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TUAZKOL24XB6QWE2SV6QP44UUC","target":"record","payload":{"canonical_record":{"source":{"id":"2112.13706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T14:28:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"16e08fc24dc60af0ff6c1e1ceff176b095a5f00443435be64a78e8b2216012ac","abstract_canon_sha256":"4165159f732f27635973a743826d3f60d73c2b6eb8db93296e4f5f2faffdee9f"},"schema_version":"1.0"},"canonical_sha256":"9d0195397ae5c3e8589a957d07f394a08c79a45b55ad99e01145aaecf8cf1346","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:26.526996Z","signature_b64":"rDOP7OZz9ki/tDeeuB++l6g1OTIuNnIomjL1LgDwdolo5W9DlHWb0o87O4StJX428wK29KNs4cv1xh3x5YflCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d0195397ae5c3e8589a957d07f394a08c79a45b55ad99e01145aaecf8cf1346","last_reissued_at":"2026-07-05T03:54:26.526519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:26.526519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.13706","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:54:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZrRUhJKEEOOimE8r0x4gbXpz2+fWuSZSUsidRECGI62iWUtNsSfRRziLq1EJBj3mrmRWGKvZKFlLow6Wa4LCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:59:47.624375Z"},"content_sha256":"ebb2abf20514d6287ff9ad6a4ff6768915518b3d9ae1ec57940503dee68ed2f6","schema_version":"1.0","event_id":"sha256:ebb2abf20514d6287ff9ad6a4ff6768915518b3d9ae1ec57940503dee68ed2f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TUAZKOL24XB6QWE2SV6QP44UUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Image Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Akhilesh Bhardwaj, Harsh Raj, Janhavi Dadhania, Prabuchandran KJ","submitted_at":"2021-12-27T14:28:04Z","abstract_excerpt":"While a lot of work has been done on developing models to tackle the problem of Visual Question Answering, the ability of these models to relate the question to the image features still remain less explored. We present an empirical study of different feature extraction methods with different loss functions. We propose New dataset for the task of Visual Question Answering with multiple image inputs having only one ground truth, and benchmark our results on them. Our final model utilising Resnet + RCNN image features and Bert embeddings, inspired from stacked attention network gives 39% word acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13706","kind":"arxiv","version":2},"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/2112.13706/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":"2026-07-05T03:54:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m40m6khfOYrmqK8VBiHXpalG9kGpeWk+pzQx0f402NWfiYdh7H26CN9Nnrrivgv5/omgCB+tYxNNm1RrxfENCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:59:47.624894Z"},"content_sha256":"b95e535cc032fe102001c6d0cf6ec2f2aa920e092988bf6f5c5f24ef6b08b3bc","schema_version":"1.0","event_id":"sha256:b95e535cc032fe102001c6d0cf6ec2f2aa920e092988bf6f5c5f24ef6b08b3bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUAZKOL24XB6QWE2SV6QP44UUC/bundle.json","state_url":"https://pith.science/pith/TUAZKOL24XB6QWE2SV6QP44UUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUAZKOL24XB6QWE2SV6QP44UUC/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":"2026-08-10T10:59:47Z","links":{"resolver":"https://pith.science/pith/TUAZKOL24XB6QWE2SV6QP44UUC","bundle":"https://pith.science/pith/TUAZKOL24XB6QWE2SV6QP44UUC/bundle.json","state":"https://pith.science/pith/TUAZKOL24XB6QWE2SV6QP44UUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUAZKOL24XB6QWE2SV6QP44UUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TUAZKOL24XB6QWE2SV6QP44UUC","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":"4165159f732f27635973a743826d3f60d73c2b6eb8db93296e4f5f2faffdee9f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T14:28:04Z","title_canon_sha256":"16e08fc24dc60af0ff6c1e1ceff176b095a5f00443435be64a78e8b2216012ac"},"schema_version":"1.0","source":{"id":"2112.13706","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13706","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13706v2","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13706","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"pith_short_12","alias_value":"TUAZKOL24XB6","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"pith_short_16","alias_value":"TUAZKOL24XB6QWE2","created_at":"2026-07-05T03:54:26Z"},{"alias_kind":"pith_short_8","alias_value":"TUAZKOL2","created_at":"2026-07-05T03:54:26Z"}],"graph_snapshots":[{"event_id":"sha256:b95e535cc032fe102001c6d0cf6ec2f2aa920e092988bf6f5c5f24ef6b08b3bc","target":"graph","created_at":"2026-07-05T03:54:26Z","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/2112.13706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While a lot of work has been done on developing models to tackle the problem of Visual Question Answering, the ability of these models to relate the question to the image features still remain less explored. We present an empirical study of different feature extraction methods with different loss functions. We propose New dataset for the task of Visual Question Answering with multiple image inputs having only one ground truth, and benchmark our results on them. Our final model utilising Resnet + RCNN image features and Bert embeddings, inspired from stacked attention network gives 39% word acc","authors_text":"Akhilesh Bhardwaj, Harsh Raj, Janhavi Dadhania, Prabuchandran KJ","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T14:28:04Z","title":"Multi-Image Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13706","kind":"arxiv","version":2},"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:ebb2abf20514d6287ff9ad6a4ff6768915518b3d9ae1ec57940503dee68ed2f6","target":"record","created_at":"2026-07-05T03:54:26Z","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":"4165159f732f27635973a743826d3f60d73c2b6eb8db93296e4f5f2faffdee9f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T14:28:04Z","title_canon_sha256":"16e08fc24dc60af0ff6c1e1ceff176b095a5f00443435be64a78e8b2216012ac"},"schema_version":"1.0","source":{"id":"2112.13706","kind":"arxiv","version":2}},"canonical_sha256":"9d0195397ae5c3e8589a957d07f394a08c79a45b55ad99e01145aaecf8cf1346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d0195397ae5c3e8589a957d07f394a08c79a45b55ad99e01145aaecf8cf1346","first_computed_at":"2026-07-05T03:54:26.526519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:26.526519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDOP7OZz9ki/tDeeuB++l6g1OTIuNnIomjL1LgDwdolo5W9DlHWb0o87O4StJX428wK29KNs4cv1xh3x5YflCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:26.526996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13706","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebb2abf20514d6287ff9ad6a4ff6768915518b3d9ae1ec57940503dee68ed2f6","sha256:b95e535cc032fe102001c6d0cf6ec2f2aa920e092988bf6f5c5f24ef6b08b3bc"],"state_sha256":"58daee72f14745851572ffc5904e917d006dc34bd3b36f3c074d8e38765c9eb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzgYZXWmImVpJfEo3Y2zTyABymVsjGyh6j+TXb9IdIwTzlTmxvG3dIka1lMx3SFQ/P1P9GLLe0e03LQYaRaWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:59:47.631121Z","bundle_sha256":"00881c0267c4f8a74df64842626fd755142922d8a844be579678b3211f5a2a14"}}