{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IPID6YTHRH5GYJMOOVESHJ543J","short_pith_number":"pith:IPID6YTH","schema_version":"1.0","canonical_sha256":"43d03f626789fa6c258e754923a7bcda57c425b654f8be4c9bca7d1f963f6713","source":{"kind":"arxiv","id":"2001.08034","version":1},"attestation_state":"computed","paper":{"title":"ManyModalQA: Modality Disambiguation and QA over Diverse Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Akshay Jain, Darryl Hannan, Mohit Bansal","submitted_at":"2020-01-22T14:39:28Z","abstract_excerpt":"We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs. Our questions are ambiguous, in that the modality that contains the answer is not easily determined based solely upon the question. To demonstrate this ambiguity, we construct a modality selector (or disambiguator) network, and this model gets substantially lower accuracy on our challenge set, compared to existi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2001.08034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-22T14:39:28Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"50216fe6550cfed5bcdff7634c9ba1de1b21f00afc7d2c5f93a8e500517b8a57","abstract_canon_sha256":"ae78e7e74894bb1537e6ba595a3ccf08dfb03ca3b7b30ff3f7edd39a62563326"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:07.189020Z","signature_b64":"BU/3iJGDDb7yFceAvx7VW7PbPwnBphdLgQEUnlowlVHoLpUdn1VP4C2AzMBZG7gemKsKkrpol/F2Iw3P/64EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43d03f626789fa6c258e754923a7bcda57c425b654f8be4c9bca7d1f963f6713","last_reissued_at":"2026-07-05T00:35:07.188671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:07.188671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ManyModalQA: Modality Disambiguation and QA over Diverse Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Akshay Jain, Darryl Hannan, Mohit Bansal","submitted_at":"2020-01-22T14:39:28Z","abstract_excerpt":"We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs. Our questions are ambiguous, in that the modality that contains the answer is not easily determined based solely upon the question. To demonstrate this ambiguity, we construct a modality selector (or disambiguator) network, and this model gets substantially lower accuracy on our challenge set, compared to existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08034","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.08034/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2001.08034","created_at":"2026-07-05T00:35:07.188725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08034v1","created_at":"2026-07-05T00:35:07.188725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08034","created_at":"2026-07-05T00:35:07.188725+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPID6YTHRH5G","created_at":"2026-07-05T00:35:07.188725+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPID6YTHRH5GYJMO","created_at":"2026-07-05T00:35:07.188725+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPID6YTH","created_at":"2026-07-05T00:35:07.188725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J","json":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J.json","graph_json":"https://pith.science/api/pith-number/IPID6YTHRH5GYJMOOVESHJ543J/graph.json","events_json":"https://pith.science/api/pith-number/IPID6YTHRH5GYJMOOVESHJ543J/events.json","paper":"https://pith.science/paper/IPID6YTH"},"agent_actions":{"view_html":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J","download_json":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J.json","view_paper":"https://pith.science/paper/IPID6YTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08034&json=true","fetch_graph":"https://pith.science/api/pith-number/IPID6YTHRH5GYJMOOVESHJ543J/graph.json","fetch_events":"https://pith.science/api/pith-number/IPID6YTHRH5GYJMOOVESHJ543J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J/action/storage_attestation","attest_author":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J/action/author_attestation","sign_citation":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J/action/citation_signature","submit_replication":"https://pith.science/pith/IPID6YTHRH5GYJMOOVESHJ543J/action/replication_record"}},"created_at":"2026-07-05T00:35:07.188725+00:00","updated_at":"2026-07-05T00:35:07.188725+00:00"}