{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:62UFQB6AMSA64YG25AU3NNQSRP","short_pith_number":"pith:62UFQB6A","canonical_record":{"source":{"id":"1705.00464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T10:43:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6b6bc0eaf11f791807e02e9fef0dc5239d782521ef94afd6682e6f7f41a5d8bc","abstract_canon_sha256":"7bd4022a9215863ac8a52642bbf425b180fe6d8d6b4231ba66f52e7ca12622a1"},"schema_version":"1.0"},"canonical_sha256":"f6a85807c06481ee60dae829b6b6128bd70b9f0c9d5a037599a8e8b25fe6b24c","source":{"kind":"arxiv","id":"1705.00464","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00464","created_at":"2026-05-18T00:35:04Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00464v2","created_at":"2026-05-18T00:35:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00464","created_at":"2026-05-18T00:35:04Z"},{"alias_kind":"pith_short_12","alias_value":"62UFQB6AMSA6","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"62UFQB6AMSA64YG2","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"62UFQB6A","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:62UFQB6AMSA64YG25AU3NNQSRP","target":"record","payload":{"canonical_record":{"source":{"id":"1705.00464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T10:43:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6b6bc0eaf11f791807e02e9fef0dc5239d782521ef94afd6682e6f7f41a5d8bc","abstract_canon_sha256":"7bd4022a9215863ac8a52642bbf425b180fe6d8d6b4231ba66f52e7ca12622a1"},"schema_version":"1.0"},"canonical_sha256":"f6a85807c06481ee60dae829b6b6128bd70b9f0c9d5a037599a8e8b25fe6b24c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:04.310006Z","signature_b64":"UwrswvRiAeb7Hk7vmzBt93D6cMPjRdNRgX0hnqdjmFe4YdaPbjXcH5dfxqPMzKNQ8qoabnSxIcoANiAhQVowCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6a85807c06481ee60dae829b6b6128bd70b9f0c9d5a037599a8e8b25fe6b24c","last_reissued_at":"2026-05-18T00:35:04.309286Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:04.309286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.00464","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":"2026-05-18T00:35:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcbH2uKuGKziBGryeotpVSQJ9wdJEHWVY1C45tf0h6vWt8NDWhwpxbiAoBT3K/7hVuR+hhxfjwsTZaUT86aJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:04:07.859543Z"},"content_sha256":"ed8b29bfff6da70e0ee03bcc84ccc8335c9052715e49083792bafec11d22dae7","schema_version":"1.0","event_id":"sha256:ed8b29bfff6da70e0ee03bcc84ccc8335c9052715e49083792bafec11d22dae7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:62UFQB6AMSA64YG25AU3NNQSRP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech-Based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dengxin Dai, Luc Van Gool, Marie-Francine Moens, Ted Zhang, Tinne Tuytelaars","submitted_at":"2017-05-01T10:43:28Z","abstract_excerpt":"This paper introduces speech-based visual question answering (VQA), the task of generating an answer given an image and a spoken question. Two methods are studied: an end-to-end, deep neural network that directly uses audio waveforms as input versus a pipelined approach that performs ASR (Automatic Speech Recognition) on the question, followed by text-based visual question answering. Furthermore, we investigate the robustness of both methods by injecting various levels of noise into the spoken question and find both methods to be tolerate noise at similar levels."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00464","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":"2026-05-18T00:35:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2ZURtdmVul1zwXa0YpT2komIHfb2tXJFeKYX+60/P+LJRoJh3mdxqWG6o5/E3gweeFRicelY33wDRTXpSDvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:04:07.859903Z"},"content_sha256":"f527bc1cb90d93be19fd1728c493033ca4dfe6f57b63e47fbd15e58df59c8c60","schema_version":"1.0","event_id":"sha256:f527bc1cb90d93be19fd1728c493033ca4dfe6f57b63e47fbd15e58df59c8c60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62UFQB6AMSA64YG25AU3NNQSRP/bundle.json","state_url":"https://pith.science/pith/62UFQB6AMSA64YG25AU3NNQSRP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62UFQB6AMSA64YG25AU3NNQSRP/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":"2026-05-30T15:04:07Z","links":{"resolver":"https://pith.science/pith/62UFQB6AMSA64YG25AU3NNQSRP","bundle":"https://pith.science/pith/62UFQB6AMSA64YG25AU3NNQSRP/bundle.json","state":"https://pith.science/pith/62UFQB6AMSA64YG25AU3NNQSRP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62UFQB6AMSA64YG25AU3NNQSRP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:62UFQB6AMSA64YG25AU3NNQSRP","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":"7bd4022a9215863ac8a52642bbf425b180fe6d8d6b4231ba66f52e7ca12622a1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T10:43:28Z","title_canon_sha256":"6b6bc0eaf11f791807e02e9fef0dc5239d782521ef94afd6682e6f7f41a5d8bc"},"schema_version":"1.0","source":{"id":"1705.00464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.00464","created_at":"2026-05-18T00:35:04Z"},{"alias_kind":"arxiv_version","alias_value":"1705.00464v2","created_at":"2026-05-18T00:35:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00464","created_at":"2026-05-18T00:35:04Z"},{"alias_kind":"pith_short_12","alias_value":"62UFQB6AMSA6","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"62UFQB6AMSA64YG2","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"62UFQB6A","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:f527bc1cb90d93be19fd1728c493033ca4dfe6f57b63e47fbd15e58df59c8c60","target":"graph","created_at":"2026-05-18T00:35:04Z","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":"This paper introduces speech-based visual question answering (VQA), the task of generating an answer given an image and a spoken question. Two methods are studied: an end-to-end, deep neural network that directly uses audio waveforms as input versus a pipelined approach that performs ASR (Automatic Speech Recognition) on the question, followed by text-based visual question answering. Furthermore, we investigate the robustness of both methods by injecting various levels of noise into the spoken question and find both methods to be tolerate noise at similar levels.","authors_text":"Dengxin Dai, Luc Van Gool, Marie-Francine Moens, Ted Zhang, Tinne Tuytelaars","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T10:43:28Z","title":"Speech-Based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00464","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:ed8b29bfff6da70e0ee03bcc84ccc8335c9052715e49083792bafec11d22dae7","target":"record","created_at":"2026-05-18T00:35:04Z","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":"7bd4022a9215863ac8a52642bbf425b180fe6d8d6b4231ba66f52e7ca12622a1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T10:43:28Z","title_canon_sha256":"6b6bc0eaf11f791807e02e9fef0dc5239d782521ef94afd6682e6f7f41a5d8bc"},"schema_version":"1.0","source":{"id":"1705.00464","kind":"arxiv","version":2}},"canonical_sha256":"f6a85807c06481ee60dae829b6b6128bd70b9f0c9d5a037599a8e8b25fe6b24c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6a85807c06481ee60dae829b6b6128bd70b9f0c9d5a037599a8e8b25fe6b24c","first_computed_at":"2026-05-18T00:35:04.309286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:04.309286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UwrswvRiAeb7Hk7vmzBt93D6cMPjRdNRgX0hnqdjmFe4YdaPbjXcH5dfxqPMzKNQ8qoabnSxIcoANiAhQVowCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:04.310006Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.00464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed8b29bfff6da70e0ee03bcc84ccc8335c9052715e49083792bafec11d22dae7","sha256:f527bc1cb90d93be19fd1728c493033ca4dfe6f57b63e47fbd15e58df59c8c60"],"state_sha256":"3598f51cc143d28420f6b2075c5c5f7142bcf05064a8b5e285ea4fa9f9dd1183"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1eW+yuAGiaJbxzDRX9VpY0d9+RnQZXfTKsY+YlHggjc6r0XVBco3i+/L6iLx/FimiXp5m8fxSuKZT5HpBTiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:04:07.862131Z","bundle_sha256":"ab54001f888cd2be0e10c444e7a66115b4dc627bd50472350017548e62b6468c"}}