{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TX6VV6UVAQAEXWHWNHUZOQ6DMN","short_pith_number":"pith:TX6VV6UV","canonical_record":{"source":{"id":"1810.03821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-09T05:51:08Z","cross_cats_sorted":[],"title_canon_sha256":"ab7ce198e4f8cff1aef3755e48d6a237406391b4e7ebe3562f7d3617f937b2c6","abstract_canon_sha256":"a363038f6df16cbac8f3e03e3956f78b6836b8df2d082871f79a103aedb885f1"},"schema_version":"1.0"},"canonical_sha256":"9dfd5afa9504004bd8f669e99743c36374fd6e3a235a44ed39755e0ae344907f","source":{"kind":"arxiv","id":"1810.03821","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03821","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03821v1","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03821","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"TX6VV6UVAQAE","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TX6VV6UVAQAEXWHW","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TX6VV6UV","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TX6VV6UVAQAEXWHWNHUZOQ6DMN","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-09T05:51:08Z","cross_cats_sorted":[],"title_canon_sha256":"ab7ce198e4f8cff1aef3755e48d6a237406391b4e7ebe3562f7d3617f937b2c6","abstract_canon_sha256":"a363038f6df16cbac8f3e03e3956f78b6836b8df2d082871f79a103aedb885f1"},"schema_version":"1.0"},"canonical_sha256":"9dfd5afa9504004bd8f669e99743c36374fd6e3a235a44ed39755e0ae344907f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:44.448556Z","signature_b64":"fj6ufGRt+MLEjaXeAYbmSDRLAIO+ME0bKhpOFUlhkk1t3CA/oMFeuEX31KHGdn20aeHjV5jJ0YIt/9JU4uCGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dfd5afa9504004bd8f669e99743c36374fd6e3a235a44ed39755e0ae344907f","last_reissued_at":"2026-05-18T00:03:44.447958Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:44.447958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03821","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":"2026-05-18T00:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGiKdGcKRpYbcxSOiuiGzBUIC7+546+zokOxEPRVA6YjcMOrJHcuDzty64ApAR9ywaV3c9aDZn83NsF+x8lUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:57:43.508147Z"},"content_sha256":"04c30f8413e49448eae0e14d99364a7b93ea056b75a38454b0e47892526da5e8","schema_version":"1.0","event_id":"sha256:04c30f8413e49448eae0e14d99364a7b93ea056b75a38454b0e47892526da5e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TX6VV6UVAQAEXWHWNHUZOQ6DMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowing Where to Look? Analysis on Attention of Visual Question Answering System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Wei Li, Xiangzhong Fang, Zehuan Yuan","submitted_at":"2018-10-09T05:51:08Z","abstract_excerpt":"Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions. Analyzing attention maps offers us a perspective to find out limitations of current VQA systems and an opportunity to further improve them. In this paper, we select two state-of-the-art VQA approaches with attention mechanisms to study their robustness and disadvantages by visualizing and analyzing their estimated attention maps. We find that both methods are sensitive to features, and simultaneously, they perform badly for counting and multi-ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03821","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":"2026-05-18T00:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y1nx/iUGg/lBvNNmlHVm2XqrhlDyv/zXM1SZZddVweSYLzDmUZaeMq867pD8dOpxNLAoGZBv52s6LVvmyje1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:57:43.508841Z"},"content_sha256":"a1a6ac561ba2758bc1b0be192647fbcdfd09fa1b16ea0d880bf56b7946d582bf","schema_version":"1.0","event_id":"sha256:a1a6ac561ba2758bc1b0be192647fbcdfd09fa1b16ea0d880bf56b7946d582bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN/bundle.json","state_url":"https://pith.science/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN/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":"2026-05-29T19:57:43Z","links":{"resolver":"https://pith.science/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN","bundle":"https://pith.science/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN/bundle.json","state":"https://pith.science/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TX6VV6UVAQAEXWHWNHUZOQ6DMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TX6VV6UVAQAEXWHWNHUZOQ6DMN","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":"a363038f6df16cbac8f3e03e3956f78b6836b8df2d082871f79a103aedb885f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-09T05:51:08Z","title_canon_sha256":"ab7ce198e4f8cff1aef3755e48d6a237406391b4e7ebe3562f7d3617f937b2c6"},"schema_version":"1.0","source":{"id":"1810.03821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03821","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03821v1","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03821","created_at":"2026-05-18T00:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"TX6VV6UVAQAE","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TX6VV6UVAQAEXWHW","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TX6VV6UV","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:a1a6ac561ba2758bc1b0be192647fbcdfd09fa1b16ea0d880bf56b7946d582bf","target":"graph","created_at":"2026-05-18T00:03:44Z","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":"Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions. Analyzing attention maps offers us a perspective to find out limitations of current VQA systems and an opportunity to further improve them. In this paper, we select two state-of-the-art VQA approaches with attention mechanisms to study their robustness and disadvantages by visualizing and analyzing their estimated attention maps. We find that both methods are sensitive to features, and simultaneously, they perform badly for counting and multi-ob","authors_text":"Changhu Wang, Wei Li, Xiangzhong Fang, Zehuan Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-09T05:51:08Z","title":"Knowing Where to Look? Analysis on Attention of Visual Question Answering System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03821","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":"sha256:04c30f8413e49448eae0e14d99364a7b93ea056b75a38454b0e47892526da5e8","target":"record","created_at":"2026-05-18T00:03:44Z","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":"a363038f6df16cbac8f3e03e3956f78b6836b8df2d082871f79a103aedb885f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-09T05:51:08Z","title_canon_sha256":"ab7ce198e4f8cff1aef3755e48d6a237406391b4e7ebe3562f7d3617f937b2c6"},"schema_version":"1.0","source":{"id":"1810.03821","kind":"arxiv","version":1}},"canonical_sha256":"9dfd5afa9504004bd8f669e99743c36374fd6e3a235a44ed39755e0ae344907f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dfd5afa9504004bd8f669e99743c36374fd6e3a235a44ed39755e0ae344907f","first_computed_at":"2026-05-18T00:03:44.447958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:44.447958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fj6ufGRt+MLEjaXeAYbmSDRLAIO+ME0bKhpOFUlhkk1t3CA/oMFeuEX31KHGdn20aeHjV5jJ0YIt/9JU4uCGBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:44.448556Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04c30f8413e49448eae0e14d99364a7b93ea056b75a38454b0e47892526da5e8","sha256:a1a6ac561ba2758bc1b0be192647fbcdfd09fa1b16ea0d880bf56b7946d582bf"],"state_sha256":"533e6c07d65f80e8bd0c6338b425878e00d7008735ac50d4121fd92470c84ba3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBbAV9XqL3JXutqFiazCrRAMFhMVhKdR4Y4jG/H5kZz9k7adYfU+oFVGSWqnZrSy+i1RzbpwmM2U3cjqeb1vAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:57:43.512677Z","bundle_sha256":"ca43ae98b930fdfc146f48b320003b7ea0e35157ebe11770c24465a4fe202a84"}}