{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VNEQYPNOUSZAVEF6C6H6FDYDJY","short_pith_number":"pith:VNEQYPNO","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"},"canonical_sha256":"ab490c3daea4b20a90be178fe28f034e3abc363820a5f19c308354bb843def4a","source":{"kind":"arxiv","id":"1802.03803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03803","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03803v2","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03803","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"VNEQYPNOUSZA","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VNEQYPNOUSZAVEF6","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VNEQYPNO","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VNEQYPNOUSZAVEF6C6H6FDYDJY","target":"record","payload":{"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"},"canonical_sha256":"ab490c3daea4b20a90be178fe28f034e3abc363820a5f19c308354bb843def4a","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"},"source_kind":"arxiv","source_id":"1802.03803","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":"2026-05-18T00:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7x8khXNy9ZWWOpJHGep4asAttFQUscoQhHXYdsvATYobCPzyIlnOiZ+j6RA6xJY1f8DyGRL361o9oEAh0YEOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:13:27.648962Z"},"content_sha256":"dc877d190da5be1953efa10e895d5e7c461fbe5e086fd2ba366bf58dbf9d9c49","schema_version":"1.0","event_id":"sha256:dc877d190da5be1953efa10e895d5e7c461fbe5e086fd2ba366bf58dbf9d9c49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VNEQYPNOUSZAVEF6C6H6FDYDJY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"79wfQwxYkJtrEmThvyVcpZeDJuiW2lYUI02Jo+33RUwA0frKdT+ReLUwttfFYIG1D90pgM7nA+8nPeB1yxj+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:13:27.649290Z"},"content_sha256":"7da2b3c069d1582c2366d2af6f72e9fa7d0054c3b64191bdf334fd8ff866a9b3","schema_version":"1.0","event_id":"sha256:7da2b3c069d1582c2366d2af6f72e9fa7d0054c3b64191bdf334fd8ff866a9b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/bundle.json","state_url":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/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":"2026-06-02T03:13:27Z","links":{"resolver":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY","bundle":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/bundle.json","state":"https://pith.science/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNEQYPNOUSZAVEF6C6H6FDYDJY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VNEQYPNOUSZAVEF6C6H6FDYDJY","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":"d55d3dff973104d9f8e3db64d1e17ff59446e6add932df8ccf54bd483817f3e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-11T19:40:16Z","title_canon_sha256":"e0eca9a54f9ded7bb952a249a83d0fe4c373e9e6241badbc00ee4713f8ae8a83"},"schema_version":"1.0","source":{"id":"1802.03803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03803","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03803v2","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03803","created_at":"2026-05-18T00:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"VNEQYPNOUSZA","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VNEQYPNOUSZAVEF6","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VNEQYPNO","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:7da2b3c069d1582c2366d2af6f72e9fa7d0054c3b64191bdf334fd8ff866a9b3","target":"graph","created_at":"2026-05-18T00:19:32Z","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 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","authors_text":"Daniela Massiceti, N. Siddharth, Philip H.S. Torr, Puneet K. Dokania","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-11T19:40:16Z","title":"FlipDial: A Generative Model for Two-Way Visual Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03803","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:dc877d190da5be1953efa10e895d5e7c461fbe5e086fd2ba366bf58dbf9d9c49","target":"record","created_at":"2026-05-18T00:19:32Z","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":"d55d3dff973104d9f8e3db64d1e17ff59446e6add932df8ccf54bd483817f3e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-11T19:40:16Z","title_canon_sha256":"e0eca9a54f9ded7bb952a249a83d0fe4c373e9e6241badbc00ee4713f8ae8a83"},"schema_version":"1.0","source":{"id":"1802.03803","kind":"arxiv","version":2}},"canonical_sha256":"ab490c3daea4b20a90be178fe28f034e3abc363820a5f19c308354bb843def4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab490c3daea4b20a90be178fe28f034e3abc363820a5f19c308354bb843def4a","first_computed_at":"2026-05-18T00:19:32.886354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:32.886354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ocfRaKAg+cVOcP0XL89kJXB8pxElI5aOfXcURbSM0iLWJNlpa8S00XBm99udWqb0CBmhMZapdcAfcRuTaOozBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:32.886963Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc877d190da5be1953efa10e895d5e7c461fbe5e086fd2ba366bf58dbf9d9c49","sha256:7da2b3c069d1582c2366d2af6f72e9fa7d0054c3b64191bdf334fd8ff866a9b3"],"state_sha256":"3cbbbd26cb3dc11a8528f7cbef59231ee67be283af5c49ab0faa722be62bd6cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNQlxXq/WY7hBCZEyEbB4wYMxFIV4eD6rrdgC7GhrnNzdcJbMrMVCN7TxZh8nD2xFcIsE1Lm8O6bQIsxc7crAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T03:13:27.651080Z","bundle_sha256":"2a5ed13a8f4d5b40e44e7a3428a5b384812bb355032d95cb01297c08d3ebdd48"}}