{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DR4QBDMEWBKSL4QOMKRHC4V5ED","short_pith_number":"pith:DR4QBDME","schema_version":"1.0","canonical_sha256":"1c79008d84b05525f20e62a27172bd20e66ff501c72aaac61bf31fa14b3d1e81","source":{"kind":"arxiv","id":"1809.03408","version":2},"attestation_state":"computed","paper":{"title":"Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aashish Venkatesh, Barbara Plank, Elia Bruni, Raffaella Bernardi, Raquel Fern\\'andez, Ravi Shekhar, Tim Baumg\\\"artner","submitted_at":"2018-09-10T15:46:58Z","abstract_excerpt":"We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! game, a two-player game where the goal is to identify an object in a complex visual scene by asking a sequence of yes/no questions. Our visually-grounded encoder leverages synergies between guessing and asking questions, as it is trained jointly using multi-task learning. We further enrich our model via a cooperative learning regime. We show that the introduction of both the joint architecture and coop"},"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":"1809.03408","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-10T15:46:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"afe7f0963a40de5580c489fa4842b4e531dccbecb548cfa4d4d77fdf6bb8e439","abstract_canon_sha256":"63bd4862668e5165cc692279fa20b57b0792c173e9fc8f85087e7fc4e6a40623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:14.275599Z","signature_b64":"jcW+oJPafpZ5BKY+ycl2JSoGF3pA75qT+Se6a7mfcekjF2NdnZH/lZpP6+IeWAiVrE1hTK1BineZj/qcEHM+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c79008d84b05525f20e62a27172bd20e66ff501c72aaac61bf31fa14b3d1e81","last_reissued_at":"2026-05-17T23:51:14.274924Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:14.274924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aashish Venkatesh, Barbara Plank, Elia Bruni, Raffaella Bernardi, Raquel Fern\\'andez, Ravi Shekhar, Tim Baumg\\\"artner","submitted_at":"2018-09-10T15:46:58Z","abstract_excerpt":"We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! game, a two-player game where the goal is to identify an object in a complex visual scene by asking a sequence of yes/no questions. Our visually-grounded encoder leverages synergies between guessing and asking questions, as it is trained jointly using multi-task learning. We further enrich our model via a cooperative learning regime. We show that the introduction of both the joint architecture and coop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03408","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":"1809.03408","created_at":"2026-05-17T23:51:14.275043+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03408v2","created_at":"2026-05-17T23:51:14.275043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03408","created_at":"2026-05-17T23:51:14.275043+00:00"},{"alias_kind":"pith_short_12","alias_value":"DR4QBDMEWBKS","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DR4QBDMEWBKSL4QO","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DR4QBDME","created_at":"2026-05-18T12:32:19.392346+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/DR4QBDMEWBKSL4QOMKRHC4V5ED","json":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED.json","graph_json":"https://pith.science/api/pith-number/DR4QBDMEWBKSL4QOMKRHC4V5ED/graph.json","events_json":"https://pith.science/api/pith-number/DR4QBDMEWBKSL4QOMKRHC4V5ED/events.json","paper":"https://pith.science/paper/DR4QBDME"},"agent_actions":{"view_html":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED","download_json":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED.json","view_paper":"https://pith.science/paper/DR4QBDME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03408&json=true","fetch_graph":"https://pith.science/api/pith-number/DR4QBDMEWBKSL4QOMKRHC4V5ED/graph.json","fetch_events":"https://pith.science/api/pith-number/DR4QBDMEWBKSL4QOMKRHC4V5ED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED/action/storage_attestation","attest_author":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED/action/author_attestation","sign_citation":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED/action/citation_signature","submit_replication":"https://pith.science/pith/DR4QBDMEWBKSL4QOMKRHC4V5ED/action/replication_record"}},"created_at":"2026-05-17T23:51:14.275043+00:00","updated_at":"2026-05-17T23:51:14.275043+00:00"}