{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OQ2VUS46QWOPDGPM2UFRFNRTBN","short_pith_number":"pith:OQ2VUS46","canonical_record":{"source":{"id":"1803.08896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-23T17:17:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a29262eab80bab8f124193f80293dd935713307c00e9e00b567e0c09e052a2c8","abstract_canon_sha256":"734fce5bb83551a7960a5eb22efa896110194dc7b8fe93e79cdd3837efc098d4"},"schema_version":"1.0"},"canonical_sha256":"74355a4b9e859cf199ecd50b12b6330b50f5ce700524324a355095789ccabc54","source":{"kind":"arxiv","id":"1803.08896","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08896","created_at":"2026-05-18T00:20:18Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08896v1","created_at":"2026-05-18T00:20:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08896","created_at":"2026-05-18T00:20:18Z"},{"alias_kind":"pith_short_12","alias_value":"OQ2VUS46QWOP","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OQ2VUS46QWOPDGPM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OQ2VUS46","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OQ2VUS46QWOPDGPM2UFRFNRTBN","target":"record","payload":{"canonical_record":{"source":{"id":"1803.08896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-23T17:17:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a29262eab80bab8f124193f80293dd935713307c00e9e00b567e0c09e052a2c8","abstract_canon_sha256":"734fce5bb83551a7960a5eb22efa896110194dc7b8fe93e79cdd3837efc098d4"},"schema_version":"1.0"},"canonical_sha256":"74355a4b9e859cf199ecd50b12b6330b50f5ce700524324a355095789ccabc54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:18.273813Z","signature_b64":"8sssC+leb0TYw6rXWHGmrv+bqO+NBimyAWqt1ZseN5YPawWcghNle0lScg5YuS2EQ3Ge2X5mwBSNKfWR2buJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74355a4b9e859cf199ecd50b12b6330b50f5ce700524324a355095789ccabc54","last_reissued_at":"2026-05-18T00:20:18.273124Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:18.273124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.08896","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":"2026-05-18T00:20:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOfdfE6/QIRWOucMqyRwjiNObKhxtlW7mXluLEFpvrwmY7rCLJjVbCDK6vD6TWC3oXkOT2lAoo3zvAkuVMAMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:43:20.090102Z"},"content_sha256":"05fe8b8d9540eb6ee4d5c91f39c7be164928f4a8e61c564e89a496dbdf44199e","schema_version":"1.0","event_id":"sha256:05fe8b8d9540eb6ee4d5c91f39c7be164928f4a8e61c564e89a496dbdf44199e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OQ2VUS46QWOPDGPM2UFRFNRTBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chitta Baral, Somak Aditya, Yezhou Yang","submitted_at":"2018-03-23T17:17:16Z","abstract_excerpt":"Many vision and language tasks require commonsense reasoning beyond data-driven image and natural language processing. Here we adopt Visual Question Answering (VQA) as an example task, where a system is expected to answer a question in natural language about an image. Current state-of-the-art systems attempted to solve the task using deep neural architectures and achieved promising performance. However, the resulting systems are generally opaque and they struggle in understanding questions for which extra knowledge is required. In this paper, we present an explicit reasoning layer on top of a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08896","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":"2026-05-18T00:20:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8v6nUL3kl6TlIPbmdl2pT3mxgi6dOo36X6DN6jfY4r7e9tyHluy1qgQ/XG2Exc3wa3kMJl+3Bx1UI+g9skB4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:43:20.090487Z"},"content_sha256":"2b9a5c2a36694d13b09fddfb92af148246118d98e899b65125984e48601fd56f","schema_version":"1.0","event_id":"sha256:2b9a5c2a36694d13b09fddfb92af148246118d98e899b65125984e48601fd56f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN/bundle.json","state_url":"https://pith.science/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN/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":"2026-05-25T11:43:20Z","links":{"resolver":"https://pith.science/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN","bundle":"https://pith.science/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN/bundle.json","state":"https://pith.science/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQ2VUS46QWOPDGPM2UFRFNRTBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OQ2VUS46QWOPDGPM2UFRFNRTBN","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":"734fce5bb83551a7960a5eb22efa896110194dc7b8fe93e79cdd3837efc098d4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-23T17:17:16Z","title_canon_sha256":"a29262eab80bab8f124193f80293dd935713307c00e9e00b567e0c09e052a2c8"},"schema_version":"1.0","source":{"id":"1803.08896","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.08896","created_at":"2026-05-18T00:20:18Z"},{"alias_kind":"arxiv_version","alias_value":"1803.08896v1","created_at":"2026-05-18T00:20:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08896","created_at":"2026-05-18T00:20:18Z"},{"alias_kind":"pith_short_12","alias_value":"OQ2VUS46QWOP","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OQ2VUS46QWOPDGPM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OQ2VUS46","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:2b9a5c2a36694d13b09fddfb92af148246118d98e899b65125984e48601fd56f","target":"graph","created_at":"2026-05-18T00:20:18Z","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":"Many vision and language tasks require commonsense reasoning beyond data-driven image and natural language processing. Here we adopt Visual Question Answering (VQA) as an example task, where a system is expected to answer a question in natural language about an image. Current state-of-the-art systems attempted to solve the task using deep neural architectures and achieved promising performance. However, the resulting systems are generally opaque and they struggle in understanding questions for which extra knowledge is required. In this paper, we present an explicit reasoning layer on top of a ","authors_text":"Chitta Baral, Somak Aditya, Yezhou Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-23T17:17:16Z","title":"Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08896","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":"sha256:05fe8b8d9540eb6ee4d5c91f39c7be164928f4a8e61c564e89a496dbdf44199e","target":"record","created_at":"2026-05-18T00:20:18Z","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":"734fce5bb83551a7960a5eb22efa896110194dc7b8fe93e79cdd3837efc098d4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-23T17:17:16Z","title_canon_sha256":"a29262eab80bab8f124193f80293dd935713307c00e9e00b567e0c09e052a2c8"},"schema_version":"1.0","source":{"id":"1803.08896","kind":"arxiv","version":1}},"canonical_sha256":"74355a4b9e859cf199ecd50b12b6330b50f5ce700524324a355095789ccabc54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74355a4b9e859cf199ecd50b12b6330b50f5ce700524324a355095789ccabc54","first_computed_at":"2026-05-18T00:20:18.273124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:18.273124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8sssC+leb0TYw6rXWHGmrv+bqO+NBimyAWqt1ZseN5YPawWcghNle0lScg5YuS2EQ3Ge2X5mwBSNKfWR2buJAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:18.273813Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.08896","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05fe8b8d9540eb6ee4d5c91f39c7be164928f4a8e61c564e89a496dbdf44199e","sha256:2b9a5c2a36694d13b09fddfb92af148246118d98e899b65125984e48601fd56f"],"state_sha256":"57760357a9cb6562a6d2327c2c6868a7e512539867a2697c479f9e64df0af041"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+/F+Ke9N5Nale8E/9iw0L6itJkF4Y9Ogh4DbW721U7MB29Fa39aI2Tg3o8lvejzrRueDhW7Nu0bBtdjvO5LDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:43:20.092816Z","bundle_sha256":"f0a097b324c3bbd8a56b8c3cf05c8e46b3df0ccc9dafc379347137693a78c660"}}