{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7C2Z6IMDWGVWSPUDWQTKBQ7MV3","short_pith_number":"pith:7C2Z6IMD","schema_version":"1.0","canonical_sha256":"f8b59f2183b1ab693e83b426a0c3ecaeef8c029d4dcca725529b84e7e4a781d4","source":{"kind":"arxiv","id":"2111.11576","version":1},"attestation_state":"computed","paper":{"title":"Building Goal-Oriented Dialogue Systems with Situated Visual Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Arijit Biswas, Emre Barut, Jan Jezabek, Sanchit Agarwal, Shuyang Gao, Tagyoung Chung","submitted_at":"2021-11-22T23:30:52Z","abstract_excerpt":"Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation of agents are required to also understand screen context in order to provide a proper interactive experience, and better understand users' goals. In this paper, we propose a novel multimodal conversational framework, where the dialogue agent's next action and their arguments are derived jointly conditioned both on the conversational and the visual context. Specifically, we propose a new model, that can reason over the"},"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":"2111.11576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T23:30:52Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ffb02e9f936ce7039845065f41cdf1e11bf7f7016dbcf87c4a73f883886d6d36","abstract_canon_sha256":"f6be3ab7da09d681328a19034a1b91e5eacd394e8c5243fd97d25b912ed7fdd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:55.073362Z","signature_b64":"EB/UGeY6OTVLLa3c1BLIykxwoZ+FqSAADzO+KVQLwRD8YnyrY3CehP9CVA5WOm2EPngLsAIAtFii0CShB5/gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b59f2183b1ab693e83b426a0c3ecaeef8c029d4dcca725529b84e7e4a781d4","last_reissued_at":"2026-07-05T03:34:55.072947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:55.072947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Goal-Oriented Dialogue Systems with Situated Visual Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Arijit Biswas, Emre Barut, Jan Jezabek, Sanchit Agarwal, Shuyang Gao, Tagyoung Chung","submitted_at":"2021-11-22T23:30:52Z","abstract_excerpt":"Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation of agents are required to also understand screen context in order to provide a proper interactive experience, and better understand users' goals. In this paper, we propose a novel multimodal conversational framework, where the dialogue agent's next action and their arguments are derived jointly conditioned both on the conversational and the visual context. Specifically, we propose a new model, that can reason over the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11576","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/2111.11576/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":"2111.11576","created_at":"2026-07-05T03:34:55.073003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11576v1","created_at":"2026-07-05T03:34:55.073003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11576","created_at":"2026-07-05T03:34:55.073003+00:00"},{"alias_kind":"pith_short_12","alias_value":"7C2Z6IMDWGVW","created_at":"2026-07-05T03:34:55.073003+00:00"},{"alias_kind":"pith_short_16","alias_value":"7C2Z6IMDWGVWSPUD","created_at":"2026-07-05T03:34:55.073003+00:00"},{"alias_kind":"pith_short_8","alias_value":"7C2Z6IMD","created_at":"2026-07-05T03:34:55.073003+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/7C2Z6IMDWGVWSPUDWQTKBQ7MV3","json":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3.json","graph_json":"https://pith.science/api/pith-number/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/graph.json","events_json":"https://pith.science/api/pith-number/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/events.json","paper":"https://pith.science/paper/7C2Z6IMD"},"agent_actions":{"view_html":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3","download_json":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3.json","view_paper":"https://pith.science/paper/7C2Z6IMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11576&json=true","fetch_graph":"https://pith.science/api/pith-number/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/graph.json","fetch_events":"https://pith.science/api/pith-number/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/action/storage_attestation","attest_author":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/action/author_attestation","sign_citation":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/action/citation_signature","submit_replication":"https://pith.science/pith/7C2Z6IMDWGVWSPUDWQTKBQ7MV3/action/replication_record"}},"created_at":"2026-07-05T03:34:55.073003+00:00","updated_at":"2026-07-05T03:34:55.073003+00:00"}