{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RYW4LGQGU6TFRXQAJXKEF45ZBA","short_pith_number":"pith:RYW4LGQG","canonical_record":{"source":{"id":"1705.03865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-10T17:30:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4a462e933c33b07a56f94d6c1e82b616ef3f266e2c631ef53d4992badbc61774","abstract_canon_sha256":"4f1b7936baa30bc9daeda2eb949c13f2f22713d95c835484499579a85c1af642"},"schema_version":"1.0"},"canonical_sha256":"8e2dc59a06a7a658de004dd442f3b9081b2605dabb0d45dc177a410e1af16e0b","source":{"kind":"arxiv","id":"1705.03865","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03865","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03865v2","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03865","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"RYW4LGQGU6TF","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RYW4LGQGU6TFRXQA","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RYW4LGQG","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RYW4LGQGU6TFRXQAJXKEF45ZBA","target":"record","payload":{"canonical_record":{"source":{"id":"1705.03865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-10T17:30:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4a462e933c33b07a56f94d6c1e82b616ef3f266e2c631ef53d4992badbc61774","abstract_canon_sha256":"4f1b7936baa30bc9daeda2eb949c13f2f22713d95c835484499579a85c1af642"},"schema_version":"1.0"},"canonical_sha256":"8e2dc59a06a7a658de004dd442f3b9081b2605dabb0d45dc177a410e1af16e0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:41.896233Z","signature_b64":"Khk10i80YXjRyy/akTjDAb3+UdVdM5NLwJivHWmTK8yz6mWdxwG55yGGLHGWuulqM36jnovd/j9ixps8ZcLhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2dc59a06a7a658de004dd442f3b9081b2605dabb0d45dc177a410e1af16e0b","last_reissued_at":"2026-05-18T00:44:41.895782Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:41.895782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.03865","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":"2026-05-18T00:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KVoTAPbPoeoMSyy70ixlvFFzgeTGjmz+jnxHa/ZtSZG3Z7XzCoQefQ5xKFhIIJYcKZWei8KpWAM2N/NIBaCBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:51:38.808139Z"},"content_sha256":"cefe3e6c426f8706edf90995a4c83dc5429305d03f55aec24de1ef1d5f9f8e06","schema_version":"1.0","event_id":"sha256:cefe3e6c426f8706edf90995a4c83dc5429305d03f55aec24de1ef1d5f9f8e06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RYW4LGQGU6TFRXQAJXKEF45ZBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Survey of Visual Question Answering: Datasets and Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Akshay Kumar Gupta","submitted_at":"2017-05-10T17:30:17Z","abstract_excerpt":"Visual question answering (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The first part of the survey details the various datasets for VQA and compares them along some common factors. The second part of this survey details the different approaches for VQA, classified into four types: non-deep learning models, deep learning models without attention, deep learning models with attention, and other models which do not fit into the first t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03865","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":""},"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":"2026-05-18T00:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UUiUiBofHqv37rKnofwsZkq5tj90F9Y9DpTajgO2vbQ8UFidQmcdtLjGlhETUA21pS+SCuHiuFnqHk+71QolBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:51:38.809143Z"},"content_sha256":"4d9ca4ff52ed4bd4f43db12191132a5cff38d83b6fe66c26341a7163a0da2b9b","schema_version":"1.0","event_id":"sha256:4d9ca4ff52ed4bd4f43db12191132a5cff38d83b6fe66c26341a7163a0da2b9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA/bundle.json","state_url":"https://pith.science/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA/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":"2026-08-08T22:51:38Z","links":{"resolver":"https://pith.science/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA","bundle":"https://pith.science/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA/bundle.json","state":"https://pith.science/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RYW4LGQGU6TFRXQAJXKEF45ZBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RYW4LGQGU6TFRXQAJXKEF45ZBA","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":"4f1b7936baa30bc9daeda2eb949c13f2f22713d95c835484499579a85c1af642","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-10T17:30:17Z","title_canon_sha256":"4a462e933c33b07a56f94d6c1e82b616ef3f266e2c631ef53d4992badbc61774"},"schema_version":"1.0","source":{"id":"1705.03865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03865","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03865v2","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03865","created_at":"2026-05-18T00:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"RYW4LGQGU6TF","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RYW4LGQGU6TFRXQA","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RYW4LGQG","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:4d9ca4ff52ed4bd4f43db12191132a5cff38d83b6fe66c26341a7163a0da2b9b","target":"graph","created_at":"2026-05-18T00:44:41Z","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 (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The first part of the survey details the various datasets for VQA and compares them along some common factors. The second part of this survey details the different approaches for VQA, classified into four types: non-deep learning models, deep learning models without attention, deep learning models with attention, and other models which do not fit into the first t","authors_text":"Akshay Kumar Gupta","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-10T17:30:17Z","title":"Survey of Visual Question Answering: Datasets and Techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03865","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:cefe3e6c426f8706edf90995a4c83dc5429305d03f55aec24de1ef1d5f9f8e06","target":"record","created_at":"2026-05-18T00:44:41Z","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":"4f1b7936baa30bc9daeda2eb949c13f2f22713d95c835484499579a85c1af642","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-10T17:30:17Z","title_canon_sha256":"4a462e933c33b07a56f94d6c1e82b616ef3f266e2c631ef53d4992badbc61774"},"schema_version":"1.0","source":{"id":"1705.03865","kind":"arxiv","version":2}},"canonical_sha256":"8e2dc59a06a7a658de004dd442f3b9081b2605dabb0d45dc177a410e1af16e0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e2dc59a06a7a658de004dd442f3b9081b2605dabb0d45dc177a410e1af16e0b","first_computed_at":"2026-05-18T00:44:41.895782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:41.895782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Khk10i80YXjRyy/akTjDAb3+UdVdM5NLwJivHWmTK8yz6mWdxwG55yGGLHGWuulqM36jnovd/j9ixps8ZcLhBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:41.896233Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.03865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cefe3e6c426f8706edf90995a4c83dc5429305d03f55aec24de1ef1d5f9f8e06","sha256:4d9ca4ff52ed4bd4f43db12191132a5cff38d83b6fe66c26341a7163a0da2b9b"],"state_sha256":"335e311aeffc1cc1aba330cf1e673a5986b13859c4ea947649277ff008a9c625"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FfvWOAgGD4NXRXeBGmnAHAfuuv2D+prIGdwj3Uw5kdAO89nVrYo7eVeGzAXkTYujGFbTltvYAbebjKgFPcOpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:51:38.815190Z","bundle_sha256":"dc40e7e652232d98068967860da870c2e1fcca14ff05346f876f9993c881018c"}}