{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:76MCJFKS6S3SODHEB25WQ5V3FT","short_pith_number":"pith:76MCJFKS","canonical_record":{"source":{"id":"1802.05766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-15T21:16:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"09ad53bd88f7ca1fdc197b807e0c2dbf25247c73f688961c9eea4f7ece8c201b","abstract_canon_sha256":"24e311754a30279c7430e8e17866fbe2fa542862a4d269bea04a594ae3ef38b0"},"schema_version":"1.0"},"canonical_sha256":"ff98249552f4b7270ce40ebb6876bb2ccedbf4d41ea822f07538d641694b3bfc","source":{"kind":"arxiv","id":"1802.05766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05766","created_at":"2026-05-18T00:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05766v1","created_at":"2026-05-18T00:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05766","created_at":"2026-05-18T00:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"76MCJFKS6S3S","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"76MCJFKS6S3SODHE","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"76MCJFKS","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:76MCJFKS6S3SODHEB25WQ5V3FT","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-15T21:16:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"09ad53bd88f7ca1fdc197b807e0c2dbf25247c73f688961c9eea4f7ece8c201b","abstract_canon_sha256":"24e311754a30279c7430e8e17866fbe2fa542862a4d269bea04a594ae3ef38b0"},"schema_version":"1.0"},"canonical_sha256":"ff98249552f4b7270ce40ebb6876bb2ccedbf4d41ea822f07538d641694b3bfc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:11.080088Z","signature_b64":"T+kcnHbIlqf3H+s1BrSUiKu90/grUFl/PtDuUH8hTIXR3btwQzjBtCec5Xo3v1yQaIBb0XJywHm77q54NxVuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff98249552f4b7270ce40ebb6876bb2ccedbf4d41ea822f07538d641694b3bfc","last_reissued_at":"2026-05-18T00:23:11.079335Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:11.079335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05766","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":"2026-05-18T00:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nFLmskRe/63mnXx2xSPwnrWyyd94YHwc7GgLtUqS4+dQI7zCYumhxlEqjJSB7l7uk+GWRU/FmAQmWxJeR9gYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:10:48.178827Z"},"content_sha256":"d36bb4ee1fa42f85df647272be1612b9b1600ac72e4f513669c0e8beddc154f4","schema_version":"1.0","event_id":"sha256:d36bb4ee1fa42f85df647272be1612b9b1600ac72e4f513669c0e8beddc154f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:76MCJFKS6S3SODHEB25WQ5V3FT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Count Objects in Natural Images for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Adam Pr\\\"ugel-Bennett, Jonathon Hare, Yan Zhang","submitted_at":"2018-02-15T21:16:59Z","abstract_excerpt":"Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05766","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":"2026-05-18T00:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBc6RuFl1QyrMRI2Mjgeyglgh+eIecWTsG7STRcxARuERDmSzn/7e/KoixsG4OJO8U+v2KUDw+5Yk8DsjB48AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:10:48.179170Z"},"content_sha256":"690d138ca9218cf35698258df90a59cfb762f8dabb48b7d5d41524c4dc114320","schema_version":"1.0","event_id":"sha256:690d138ca9218cf35698258df90a59cfb762f8dabb48b7d5d41524c4dc114320"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76MCJFKS6S3SODHEB25WQ5V3FT/bundle.json","state_url":"https://pith.science/pith/76MCJFKS6S3SODHEB25WQ5V3FT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76MCJFKS6S3SODHEB25WQ5V3FT/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":"2026-06-02T19:10:48Z","links":{"resolver":"https://pith.science/pith/76MCJFKS6S3SODHEB25WQ5V3FT","bundle":"https://pith.science/pith/76MCJFKS6S3SODHEB25WQ5V3FT/bundle.json","state":"https://pith.science/pith/76MCJFKS6S3SODHEB25WQ5V3FT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76MCJFKS6S3SODHEB25WQ5V3FT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:76MCJFKS6S3SODHEB25WQ5V3FT","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":"24e311754a30279c7430e8e17866fbe2fa542862a4d269bea04a594ae3ef38b0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-15T21:16:59Z","title_canon_sha256":"09ad53bd88f7ca1fdc197b807e0c2dbf25247c73f688961c9eea4f7ece8c201b"},"schema_version":"1.0","source":{"id":"1802.05766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05766","created_at":"2026-05-18T00:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05766v1","created_at":"2026-05-18T00:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05766","created_at":"2026-05-18T00:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"76MCJFKS6S3S","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"76MCJFKS6S3SODHE","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"76MCJFKS","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:690d138ca9218cf35698258df90a59cfb762f8dabb48b7d5d41524c4dc114320","target":"graph","created_at":"2026-05-18T00:23:11Z","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) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the","authors_text":"Adam Pr\\\"ugel-Bennett, Jonathon Hare, Yan Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-15T21:16:59Z","title":"Learning to Count Objects in Natural Images for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05766","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:d36bb4ee1fa42f85df647272be1612b9b1600ac72e4f513669c0e8beddc154f4","target":"record","created_at":"2026-05-18T00:23:11Z","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":"24e311754a30279c7430e8e17866fbe2fa542862a4d269bea04a594ae3ef38b0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-15T21:16:59Z","title_canon_sha256":"09ad53bd88f7ca1fdc197b807e0c2dbf25247c73f688961c9eea4f7ece8c201b"},"schema_version":"1.0","source":{"id":"1802.05766","kind":"arxiv","version":1}},"canonical_sha256":"ff98249552f4b7270ce40ebb6876bb2ccedbf4d41ea822f07538d641694b3bfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff98249552f4b7270ce40ebb6876bb2ccedbf4d41ea822f07538d641694b3bfc","first_computed_at":"2026-05-18T00:23:11.079335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:11.079335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T+kcnHbIlqf3H+s1BrSUiKu90/grUFl/PtDuUH8hTIXR3btwQzjBtCec5Xo3v1yQaIBb0XJywHm77q54NxVuBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:11.080088Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d36bb4ee1fa42f85df647272be1612b9b1600ac72e4f513669c0e8beddc154f4","sha256:690d138ca9218cf35698258df90a59cfb762f8dabb48b7d5d41524c4dc114320"],"state_sha256":"836aec240c139eadd217c2115c22e26546f2962116b7ea6aab713510877f474c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cduFosXKVmPuhkynGWju0pBEhK0mYZHPgZ8mDfdexAwKU7sgSmY634Y0zP/dXpJB55w8zJZfbzcZJWJ2+PgIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:10:48.181486Z","bundle_sha256":"e9f7fce9d9b0be8aad4a637a5a1a1ec47ff2ee89ac37ef5d183ca078c81d9a27"}}