{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:A7BSINFZSLLSWXGCGTDXMIP4AO","short_pith_number":"pith:A7BSINFZ","canonical_record":{"source":{"id":"1809.04344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T10:11:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d72e4f51b33389badab4d8b0a719d163fbb07e3ba82886b74c281a1aad676b69","abstract_canon_sha256":"285066d301b4873347e5e47223e8c9fc302bfeed5e596855c0b9f9c6e0675e9d"},"schema_version":"1.0"},"canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","source":{"kind":"arxiv","id":"1809.04344","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04344","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04344v1","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04344","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"A7BSINFZSLLS","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A7BSINFZSLLSWXGC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A7BSINFZ","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:A7BSINFZSLLSWXGCGTDXMIP4AO","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T10:11:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d72e4f51b33389badab4d8b0a719d163fbb07e3ba82886b74c281a1aad676b69","abstract_canon_sha256":"285066d301b4873347e5e47223e8c9fc302bfeed5e596855c0b9f9c6e0675e9d"},"schema_version":"1.0"},"canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:52.667887Z","signature_b64":"nzPPrPhxiGyH+PHXWazwQDdgW/jkzu0VJ2VP1BCyZW2VRIx7q0mPQtMSJImHyaY2LQ7ZULAf/pTX3n+pSNctBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","last_reissued_at":"2026-05-18T00:05:52.667233Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:52.667233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04344","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":"2026-05-18T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGo/UX+coRoDb9lx+oJ+UJSDSd0AeRPCxi/44/kJavai9wD3kzvWXxqb7WI1kL1gwUXFl5WLbD8WvJe7upwJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:19:31.450278Z"},"content_sha256":"d9b1d25b1f3a9c26b394f8529a6b40c3ebda671445b914579956bb1b530c5018","schema_version":"1.0","event_id":"sha256:d9b1d25b1f3a9c26b394f8529a6b40c3ebda671445b914579956bb1b530c5018"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:A7BSINFZSLLSWXGCGTDXMIP4AO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andreas Dengel, Moin Nabi, Sandro Pezzelle, Shailza Jolly, Tassilo Klein","submitted_at":"2018-09-12T10:11:39Z","abstract_excerpt":"We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04344","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":"2026-05-18T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olC3M7XotzoE4P18CPaGwTccEdfmg7G2cK0i1WivshY3zkr/5ugWcXoiqxNq1d8zMZ5T+0K0sLbOJGMM+wXCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:19:31.450638Z"},"content_sha256":"b056da32b3652b7a4212c70f20a30dbe57e3593c78c652779280ba0062d9b478","schema_version":"1.0","event_id":"sha256:b056da32b3652b7a4212c70f20a30dbe57e3593c78c652779280ba0062d9b478"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/bundle.json","state_url":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/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":"2026-06-02T11:19:31Z","links":{"resolver":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO","bundle":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/bundle.json","state":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A7BSINFZSLLSWXGCGTDXMIP4AO","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":"285066d301b4873347e5e47223e8c9fc302bfeed5e596855c0b9f9c6e0675e9d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T10:11:39Z","title_canon_sha256":"d72e4f51b33389badab4d8b0a719d163fbb07e3ba82886b74c281a1aad676b69"},"schema_version":"1.0","source":{"id":"1809.04344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04344","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04344v1","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04344","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"A7BSINFZSLLS","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A7BSINFZSLLSWXGC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A7BSINFZ","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:b056da32b3652b7a4212c70f20a30dbe57e3593c78c652779280ba0062d9b478","target":"graph","created_at":"2026-05-18T00:05:52Z","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":"We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected","authors_text":"Andreas Dengel, Moin Nabi, Sandro Pezzelle, Shailza Jolly, Tassilo Klein","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T10:11:39Z","title":"The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04344","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:d9b1d25b1f3a9c26b394f8529a6b40c3ebda671445b914579956bb1b530c5018","target":"record","created_at":"2026-05-18T00:05:52Z","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":"285066d301b4873347e5e47223e8c9fc302bfeed5e596855c0b9f9c6e0675e9d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T10:11:39Z","title_canon_sha256":"d72e4f51b33389badab4d8b0a719d163fbb07e3ba82886b74c281a1aad676b69"},"schema_version":"1.0","source":{"id":"1809.04344","kind":"arxiv","version":1}},"canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","first_computed_at":"2026-05-18T00:05:52.667233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:52.667233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nzPPrPhxiGyH+PHXWazwQDdgW/jkzu0VJ2VP1BCyZW2VRIx7q0mPQtMSJImHyaY2LQ7ZULAf/pTX3n+pSNctBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:52.667887Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9b1d25b1f3a9c26b394f8529a6b40c3ebda671445b914579956bb1b530c5018","sha256:b056da32b3652b7a4212c70f20a30dbe57e3593c78c652779280ba0062d9b478"],"state_sha256":"08dddf206645cad36a323e5ef66e038b355c6f54cdf51bdff3885728e51579be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SabcAZt3y0QsSRJbCW2S3BpomzcXC7NXdOf8mLBy7UMA1EKe8b0a7lu9NpMlTCgRYjr0VIJldcslSPMSl16sCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:19:31.452450Z","bundle_sha256":"b96b81120178ce7f967418a367c332abfaaef912e0a27dde834146d368d16a94"}}