{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VNEQYPNOUSZAVEF6C6H6FDYDJY","short_pith_number":"pith:VNEQYPNO","schema_version":"1.0","canonical_sha256":"ab490c3daea4b20a90be178fe28f034e3abc363820a5f19c308354bb843def4a","source":{"kind":"arxiv","id":"1802.03803","version":2},"attestation_state":"computed","paper":{"title":"FlipDial: A Generative Model for Two-Way Visual Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniela Massiceti, N. Siddharth, Philip H.S. Torr, Puneet K. Dokania","submitted_at":"2018-02-11T19:40:16Z","abstract_excerpt":"We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of the image, FlipDial learns both to answer questions and put forward questions, capable of generating entire sequences of dialogue (question-answer pairs) which are diverse and relevant to the image. To do this, FlipDial relies on a simple but surprisingly powerful idea: it uses convolutional neural networks (CNNs) to encode entire dialogues directly, implic"},"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":"1802.03803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-11T19:40:16Z","cross_cats_sorted":[],"title_canon_sha256":"e0eca9a54f9ded7bb952a249a83d0fe4c373e9e6241badbc00ee4713f8ae8a83","abstract_canon_sha256":"d55d3dff973104d9f8e3db64d1e17ff59446e6add932df8ccf54bd483817f3e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:32.886963Z","signature_b64":"ocfRaKAg+cVOcP0XL89kJXB8pxElI5aOfXcURbSM0iLWJNlpa8S00XBm99udWqb0CBmhMZapdcAfcRuTaOozBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab490c3daea4b20a90be178fe28f034e3abc363820a5f19c308354bb843def4a","last_reissued_at":"2026-05-18T00:19:32.886354Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:32.886354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlipDial: A Generative Model for Two-Way Visual Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniela Massiceti, N. Siddharth, Philip H.S. Torr, Puneet K. Dokania","submitted_at":"2018-02-11T19:40:16Z","abstract_excerpt":"We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of the image, FlipDial learns both to answer questions and put forward questions, capable of generating entire sequences of dialogue (question-answer pairs) which are diverse and relevant to the image. To do this, FlipDial relies on a simple but surprisingly powerful idea: it uses convolutional neural networks (CNNs) to encode entire dialogues directly, implic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03803","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.03803","created_at":"2026-05-18T00:19:32.886446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03803v2","created_at":"2026-05-18T00:19:32.886446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03803","created_at":"2026-05-18T00:19:32.886446+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNEQYPNOUSZA","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNEQYPNOUSZAVEF6","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNEQYPNO","created_at":"2026-05-18T12:32:59.047623+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/VNEQYPNOUSZAVEF6C6H6FDYDJY","json":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY.json","graph_json":"https://pith.science/api/pith-number/VNEQYPNOUSZAVEF6C6H6FDYDJY/graph.json","events_json":"https://pith.science/api/pith-number/VNEQYPNOUSZAVEF6C6H6FDYDJY/events.json","paper":"https://pith.science/paper/VNEQYPNO"},"agent_actions":{"view_html":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY","download_json":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY.json","view_paper":"https://pith.science/paper/VNEQYPNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03803&json=true","fetch_graph":"https://pith.science/api/pith-number/VNEQYPNOUSZAVEF6C6H6FDYDJY/graph.json","fetch_events":"https://pith.science/api/pith-number/VNEQYPNOUSZAVEF6C6H6FDYDJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/action/storage_attestation","attest_author":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/action/author_attestation","sign_citation":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/action/citation_signature","submit_replication":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/action/replication_record"}},"created_at":"2026-05-18T00:19:32.886446+00:00","updated_at":"2026-05-18T00:19:32.886446+00:00"}