{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EBGHF2VM2RO3O4GUFHIK45ITBR","short_pith_number":"pith:EBGHF2VM","canonical_record":{"source":{"id":"1709.08203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-09-24T14:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"426bba5fbb56608b6637cfcb2a950019a5c6cc5c5a011f3c71ae01abf1db4ee8","abstract_canon_sha256":"64785dd7ccd55d6478c5be2d6daad65a0570236ebf5e36fa24e16046e67a64ef"},"schema_version":"1.0"},"canonical_sha256":"204c72eaacd45db770d429d0ae75130c6c802f65766f2a56d19cbf3559746aca","source":{"kind":"arxiv","id":"1709.08203","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08203","created_at":"2026-05-18T00:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08203v1","created_at":"2026-05-18T00:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08203","created_at":"2026-05-18T00:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"EBGHF2VM2RO3","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EBGHF2VM2RO3O4GU","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EBGHF2VM","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EBGHF2VM2RO3O4GUFHIK45ITBR","target":"record","payload":{"canonical_record":{"source":{"id":"1709.08203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-09-24T14:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"426bba5fbb56608b6637cfcb2a950019a5c6cc5c5a011f3c71ae01abf1db4ee8","abstract_canon_sha256":"64785dd7ccd55d6478c5be2d6daad65a0570236ebf5e36fa24e16046e67a64ef"},"schema_version":"1.0"},"canonical_sha256":"204c72eaacd45db770d429d0ae75130c6c802f65766f2a56d19cbf3559746aca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:26.145600Z","signature_b64":"ptLXUQVTdbnmPhREibKtNZBFyq8xWrOegUzwVfFWt+YXxnAEkyRJL+g+W0bH8Zdfzyp4/4qMikoEYWhSOBigDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"204c72eaacd45db770d429d0ae75130c6c802f65766f2a56d19cbf3559746aca","last_reissued_at":"2026-05-18T00:34:26.145036Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:26.145036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.08203","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":"2026-05-18T00:34:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6b/V233EyfHs9cpslfhg32XmbEj6HPr0aQT3dY3nNloO6qJGWBEhwHARP00hZFDahJ5zlJHVqD6Uh54q8nl4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:29:59.338479Z"},"content_sha256":"80c441344d7d6c7e8716f02759e365eb14f912136f2427e77f8d407d3d6a2375","schema_version":"1.0","event_id":"sha256:80c441344d7d6c7e8716f02759e365eb14f912136f2427e77f8d407d3d6a2375"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EBGHF2VM2RO3O4GUFHIK45ITBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Survey of Recent Advances in Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shagun Sodhani, Supriya Pandhre","submitted_at":"2017-09-24T14:42:17Z","abstract_excerpt":"Visual Question Answering (VQA) presents a unique challenge as it requires the ability to understand and encode the multi-modal inputs - in terms of image processing and natural language processing. The algorithm further needs to learn how to perform reasoning over this multi-modal representation so it can answer the questions correctly. This paper presents a survey of different approaches proposed to solve the problem of Visual Question Answering. We also describe the current state of the art model in later part of paper. In particular, the paper describes the approaches taken by various algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08203","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":""},"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":"2026-05-18T00:34:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CIN4GZCKch74JR+aM/RP6u1QD8fQcTO8UUIuQ021gCAz4L9VCSVOYdobND02XrZEwUsQ/NWDCRvkqqu6LZoaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:29:59.338915Z"},"content_sha256":"35814e38558068044659b64a787e9dee704fe3841a5c28ebda39ebcf696e99ed","schema_version":"1.0","event_id":"sha256:35814e38558068044659b64a787e9dee704fe3841a5c28ebda39ebcf696e99ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBGHF2VM2RO3O4GUFHIK45ITBR/bundle.json","state_url":"https://pith.science/pith/EBGHF2VM2RO3O4GUFHIK45ITBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBGHF2VM2RO3O4GUFHIK45ITBR/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":"2026-06-05T23:29:59Z","links":{"resolver":"https://pith.science/pith/EBGHF2VM2RO3O4GUFHIK45ITBR","bundle":"https://pith.science/pith/EBGHF2VM2RO3O4GUFHIK45ITBR/bundle.json","state":"https://pith.science/pith/EBGHF2VM2RO3O4GUFHIK45ITBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBGHF2VM2RO3O4GUFHIK45ITBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EBGHF2VM2RO3O4GUFHIK45ITBR","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":"64785dd7ccd55d6478c5be2d6daad65a0570236ebf5e36fa24e16046e67a64ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-09-24T14:42:17Z","title_canon_sha256":"426bba5fbb56608b6637cfcb2a950019a5c6cc5c5a011f3c71ae01abf1db4ee8"},"schema_version":"1.0","source":{"id":"1709.08203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08203","created_at":"2026-05-18T00:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08203v1","created_at":"2026-05-18T00:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08203","created_at":"2026-05-18T00:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"EBGHF2VM2RO3","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EBGHF2VM2RO3O4GU","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EBGHF2VM","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:35814e38558068044659b64a787e9dee704fe3841a5c28ebda39ebcf696e99ed","target":"graph","created_at":"2026-05-18T00:34:26Z","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"},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) presents a unique challenge as it requires the ability to understand and encode the multi-modal inputs - in terms of image processing and natural language processing. The algorithm further needs to learn how to perform reasoning over this multi-modal representation so it can answer the questions correctly. This paper presents a survey of different approaches proposed to solve the problem of Visual Question Answering. We also describe the current state of the art model in later part of paper. In particular, the paper describes the approaches taken by various algo","authors_text":"Shagun Sodhani, Supriya Pandhre","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-09-24T14:42:17Z","title":"Survey of Recent Advances in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08203","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":"sha256:80c441344d7d6c7e8716f02759e365eb14f912136f2427e77f8d407d3d6a2375","target":"record","created_at":"2026-05-18T00:34:26Z","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":"64785dd7ccd55d6478c5be2d6daad65a0570236ebf5e36fa24e16046e67a64ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-09-24T14:42:17Z","title_canon_sha256":"426bba5fbb56608b6637cfcb2a950019a5c6cc5c5a011f3c71ae01abf1db4ee8"},"schema_version":"1.0","source":{"id":"1709.08203","kind":"arxiv","version":1}},"canonical_sha256":"204c72eaacd45db770d429d0ae75130c6c802f65766f2a56d19cbf3559746aca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"204c72eaacd45db770d429d0ae75130c6c802f65766f2a56d19cbf3559746aca","first_computed_at":"2026-05-18T00:34:26.145036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:26.145036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ptLXUQVTdbnmPhREibKtNZBFyq8xWrOegUzwVfFWt+YXxnAEkyRJL+g+W0bH8Zdfzyp4/4qMikoEYWhSOBigDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:26.145600Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.08203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80c441344d7d6c7e8716f02759e365eb14f912136f2427e77f8d407d3d6a2375","sha256:35814e38558068044659b64a787e9dee704fe3841a5c28ebda39ebcf696e99ed"],"state_sha256":"d908131f9c9d7839f771af802d5b54cabb43b097ac95439301bb2fa80aface62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1AHtFtzom1I0qAcBoMaLB1088Yp2uScNN7Ee9/SKZO2Zu9PsRFqRggMtU6+aZPFTgIeYIpk7flc/2j0k4L7DBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T23:29:59.343060Z","bundle_sha256":"6fe30a639ba303b8ef9ec790d5ab1d5fbff541d22eff02b9463c90a5d2da99d4"}}