{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5Z57TDFJWDTLYAYTDA2ESJKEPB","short_pith_number":"pith:5Z57TDFJ","canonical_record":{"source":{"id":"1606.08390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-27T18:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"13c51d4b862387694b8054dd6362e0e503729e466cd13338b8d3f8302cba2857","abstract_canon_sha256":"71e79b6d3e5b354a71aee919b776048ddad58e2217e327ecf36b5e76b906d85c"},"schema_version":"1.0"},"canonical_sha256":"ee7bf98ca9b0e6bc03131834492544785477cfbe1e16d506061a471d0c7046f7","source":{"kind":"arxiv","id":"1606.08390","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.08390","created_at":"2026-05-18T00:57:04Z"},{"alias_kind":"arxiv_version","alias_value":"1606.08390v2","created_at":"2026-05-18T00:57:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.08390","created_at":"2026-05-18T00:57:04Z"},{"alias_kind":"pith_short_12","alias_value":"5Z57TDFJWDTL","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5Z57TDFJWDTLYAYT","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5Z57TDFJ","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5Z57TDFJWDTLYAYTDA2ESJKEPB","target":"record","payload":{"canonical_record":{"source":{"id":"1606.08390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-27T18:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"13c51d4b862387694b8054dd6362e0e503729e466cd13338b8d3f8302cba2857","abstract_canon_sha256":"71e79b6d3e5b354a71aee919b776048ddad58e2217e327ecf36b5e76b906d85c"},"schema_version":"1.0"},"canonical_sha256":"ee7bf98ca9b0e6bc03131834492544785477cfbe1e16d506061a471d0c7046f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:04.284176Z","signature_b64":"ErGpC8Fd8X/qNKES4qdbNHP4WRE8LXKR+1BmgdOWZOlXaayjPsu7Yx8/5NlA/yBD5G1nE4jGGs1lUG46gtSzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee7bf98ca9b0e6bc03131834492544785477cfbe1e16d506061a471d0c7046f7","last_reissued_at":"2026-05-18T00:57:04.283580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:04.283580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.08390","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":"2026-05-18T00:57:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYcgBoQ6f+EMT4GPT41EIi4QLuwhyY8EyTHE6hKTmjbcsaH6YzNy9RXLgVT/s8HnHfBpaOMMUoqYO4b/dzYZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:30:02.999730Z"},"content_sha256":"807a578fc6d4c2b2490092d42ac6309c3189bab57d32a16fe9b01565c4e9e2a8","schema_version":"1.0","event_id":"sha256:807a578fc6d4c2b2490092d42ac6309c3189bab57d32a16fe9b01565c4e9e2a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5Z57TDFJWDTLYAYTDA2ESJKEPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Visual Question Answering Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Allan Jabri, Armand Joulin, Laurens van der Maaten","submitted_at":"2016-06-27T18:07:58Z","abstract_excerpt":"Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms designed to support \"reasoning\". For multiple-choice VQA, nearly all of these systems train a multi-class classifier on image and question features to predict an answer. This paper questions the value of these common practices and develops a simple alternative model based on binary classification. Instead of treating answers as competing choices, our model rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.08390","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":"2026-05-18T00:57:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4suYENxyngVYbjAfIcPZyZtttbV0/E0R7D+lXk38KMd81a2Tbtqvk9pKwQKOYs8hQMJlykUxPT6RG3j2gnxHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:30:03.000088Z"},"content_sha256":"202bcd189d8e2170cda54d761f04ac1a08bf010f9cf0987a6919e5ef928e5a08","schema_version":"1.0","event_id":"sha256:202bcd189d8e2170cda54d761f04ac1a08bf010f9cf0987a6919e5ef928e5a08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB/bundle.json","state_url":"https://pith.science/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB/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":"2026-06-04T06:30:03Z","links":{"resolver":"https://pith.science/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB","bundle":"https://pith.science/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB/bundle.json","state":"https://pith.science/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5Z57TDFJWDTLYAYTDA2ESJKEPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5Z57TDFJWDTLYAYTDA2ESJKEPB","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":"71e79b6d3e5b354a71aee919b776048ddad58e2217e327ecf36b5e76b906d85c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-27T18:07:58Z","title_canon_sha256":"13c51d4b862387694b8054dd6362e0e503729e466cd13338b8d3f8302cba2857"},"schema_version":"1.0","source":{"id":"1606.08390","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.08390","created_at":"2026-05-18T00:57:04Z"},{"alias_kind":"arxiv_version","alias_value":"1606.08390v2","created_at":"2026-05-18T00:57:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.08390","created_at":"2026-05-18T00:57:04Z"},{"alias_kind":"pith_short_12","alias_value":"5Z57TDFJWDTL","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5Z57TDFJWDTLYAYT","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5Z57TDFJ","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:202bcd189d8e2170cda54d761f04ac1a08bf010f9cf0987a6919e5ef928e5a08","target":"graph","created_at":"2026-05-18T00:57:04Z","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":"Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms designed to support \"reasoning\". For multiple-choice VQA, nearly all of these systems train a multi-class classifier on image and question features to predict an answer. This paper questions the value of these common practices and develops a simple alternative model based on binary classification. Instead of treating answers as competing choices, our model rec","authors_text":"Allan Jabri, Armand Joulin, Laurens van der Maaten","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-27T18:07:58Z","title":"Revisiting Visual Question Answering Baselines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.08390","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":"sha256:807a578fc6d4c2b2490092d42ac6309c3189bab57d32a16fe9b01565c4e9e2a8","target":"record","created_at":"2026-05-18T00:57:04Z","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":"71e79b6d3e5b354a71aee919b776048ddad58e2217e327ecf36b5e76b906d85c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-27T18:07:58Z","title_canon_sha256":"13c51d4b862387694b8054dd6362e0e503729e466cd13338b8d3f8302cba2857"},"schema_version":"1.0","source":{"id":"1606.08390","kind":"arxiv","version":2}},"canonical_sha256":"ee7bf98ca9b0e6bc03131834492544785477cfbe1e16d506061a471d0c7046f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee7bf98ca9b0e6bc03131834492544785477cfbe1e16d506061a471d0c7046f7","first_computed_at":"2026-05-18T00:57:04.283580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:04.283580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ErGpC8Fd8X/qNKES4qdbNHP4WRE8LXKR+1BmgdOWZOlXaayjPsu7Yx8/5NlA/yBD5G1nE4jGGs1lUG46gtSzCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:04.284176Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.08390","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:807a578fc6d4c2b2490092d42ac6309c3189bab57d32a16fe9b01565c4e9e2a8","sha256:202bcd189d8e2170cda54d761f04ac1a08bf010f9cf0987a6919e5ef928e5a08"],"state_sha256":"54930e885181546484e6fbc991bba82a1e9d98513a049974178afc6b449b64ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdyvMDnHJNXejga7VUYRhcGpxLZe6Ln8Z5LkcvU11jwMqtpbphbnJvZYC3GctdaOVUB0QaFuw6Pckandv5JGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T06:30:03.002385Z","bundle_sha256":"2591850ef21dfb7c954e1710ad13fc1b9837058e3a0ba345675706498194c267"}}