{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7RTB5YZLJHHJDSAGYR2OXOS2RS","short_pith_number":"pith:7RTB5YZL","schema_version":"1.0","canonical_sha256":"fc661ee32b49ce91c806c474ebba5a8c8bb84b0cb2024f5ea11643f113f6734f","source":{"kind":"arxiv","id":"1903.11207","version":1},"attestation_state":"computed","paper":{"title":"Information Maximizing Visual Question Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Fei-Fei, Michael Bernstein, Ranjay Krishna","submitted_at":"2019-03-27T00:57:25Z","abstract_excerpt":"Though image-to-sequence generation models have become overwhelmingly popular in human-computer communications, they suffer from strongly favoring safe generic questions (\"What is in this picture?\"). Generating uninformative but relevant questions is not sufficient or useful. We argue that a good question is one that has a tightly focused purpose --- one that is aimed at expecting a specific type of response. We build a model that maximizes mutual information between the image, the expected answer and the generated question. To overcome the non-differentiability of discrete natural language to"},"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":"1903.11207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T00:57:25Z","cross_cats_sorted":[],"title_canon_sha256":"3f3da7d7e74fa2c9b4976f110fc5e89b5cdc7e06ecf5b02fe604689e3a8670a8","abstract_canon_sha256":"feaa59dcd06fcb22c6705e90654f7550d235d47ff12dbbc268cc7f8b3cf77f08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:03.886697Z","signature_b64":"TyDSs/bfnmOo01VoLfBw6ihjfQDEyoEdUJn33hO6LhYlRE60mqvoUFwbbVbmoQzPwsuVY70kb1ILmOCHZ9sACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc661ee32b49ce91c806c474ebba5a8c8bb84b0cb2024f5ea11643f113f6734f","last_reissued_at":"2026-05-17T23:50:03.886235Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:03.886235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Maximizing Visual Question Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Fei-Fei, Michael Bernstein, Ranjay Krishna","submitted_at":"2019-03-27T00:57:25Z","abstract_excerpt":"Though image-to-sequence generation models have become overwhelmingly popular in human-computer communications, they suffer from strongly favoring safe generic questions (\"What is in this picture?\"). Generating uninformative but relevant questions is not sufficient or useful. We argue that a good question is one that has a tightly focused purpose --- one that is aimed at expecting a specific type of response. We build a model that maximizes mutual information between the image, the expected answer and the generated question. To overcome the non-differentiability of discrete natural language to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11207","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.11207","created_at":"2026-05-17T23:50:03.886299+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.11207v1","created_at":"2026-05-17T23:50:03.886299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11207","created_at":"2026-05-17T23:50:03.886299+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RTB5YZLJHHJ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RTB5YZLJHHJDSAG","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RTB5YZL","created_at":"2026-05-18T12:33:12.712433+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/7RTB5YZLJHHJDSAGYR2OXOS2RS","json":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS.json","graph_json":"https://pith.science/api/pith-number/7RTB5YZLJHHJDSAGYR2OXOS2RS/graph.json","events_json":"https://pith.science/api/pith-number/7RTB5YZLJHHJDSAGYR2OXOS2RS/events.json","paper":"https://pith.science/paper/7RTB5YZL"},"agent_actions":{"view_html":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS","download_json":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS.json","view_paper":"https://pith.science/paper/7RTB5YZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.11207&json=true","fetch_graph":"https://pith.science/api/pith-number/7RTB5YZLJHHJDSAGYR2OXOS2RS/graph.json","fetch_events":"https://pith.science/api/pith-number/7RTB5YZLJHHJDSAGYR2OXOS2RS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS/action/storage_attestation","attest_author":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS/action/author_attestation","sign_citation":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS/action/citation_signature","submit_replication":"https://pith.science/pith/7RTB5YZLJHHJDSAGYR2OXOS2RS/action/replication_record"}},"created_at":"2026-05-17T23:50:03.886299+00:00","updated_at":"2026-05-17T23:50:03.886299+00:00"}