{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JAV2TP44UYWYPWVDVS4QLO4RC6","short_pith_number":"pith:JAV2TP44","schema_version":"1.0","canonical_sha256":"482ba9bf9ca62d87daa3acb905bb9117ac290a1fd0cc048f0c92be2288c82604","source":{"kind":"arxiv","id":"2105.13073","version":2},"attestation_state":"computed","paper":{"title":"Maria: A Visual Experience Powered Conversational Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Fan Liang, Huang Hu, Xiubo Geng, Yining Chen, Zujie Liang","submitted_at":"2021-05-27T11:45:29Z","abstract_excerpt":"Arguably, the visual perception of conversational agents to the physical world is a key way for them to exhibit the human-like intelligence. Image-grounded conversation is thus proposed to address this challenge. Existing works focus on exploring the multimodal dialog models that ground the conversation on a given image. In this paper, we take a step further to study image-grounded conversation under a fully open-ended setting where no paired dialog and image are assumed available. Specifically, we present Maria, a neural conversation agent powered by the visual world experiences which are ret"},"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":"2105.13073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T11:45:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e78c6b1bb13cb9315ad1f6da36f9688791a03e77a32fb681a593068835f83fc3","abstract_canon_sha256":"3c94efdada60f33b6b6831f9f769a85d818f16c001224c9ba5732eaf754268d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:40.621123Z","signature_b64":"4M9mBQOUhEvXBQ6Hq1DGY2yRt+3/Frb/D53GNnwiC2qbVhSDPbGcS7qTvVzJFq0zPsEBGZxnoLjroflXoK+TDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"482ba9bf9ca62d87daa3acb905bb9117ac290a1fd0cc048f0c92be2288c82604","last_reissued_at":"2026-07-05T02:51:40.620576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:40.620576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maria: A Visual Experience Powered Conversational Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Fan Liang, Huang Hu, Xiubo Geng, Yining Chen, Zujie Liang","submitted_at":"2021-05-27T11:45:29Z","abstract_excerpt":"Arguably, the visual perception of conversational agents to the physical world is a key way for them to exhibit the human-like intelligence. Image-grounded conversation is thus proposed to address this challenge. Existing works focus on exploring the multimodal dialog models that ground the conversation on a given image. In this paper, we take a step further to study image-grounded conversation under a fully open-ended setting where no paired dialog and image are assumed available. Specifically, we present Maria, a neural conversation agent powered by the visual world experiences which are ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13073","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.13073/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":"2105.13073","created_at":"2026-07-05T02:51:40.620634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13073v2","created_at":"2026-07-05T02:51:40.620634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13073","created_at":"2026-07-05T02:51:40.620634+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAV2TP44UYWY","created_at":"2026-07-05T02:51:40.620634+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAV2TP44UYWYPWVD","created_at":"2026-07-05T02:51:40.620634+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAV2TP44","created_at":"2026-07-05T02:51:40.620634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6","json":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6.json","graph_json":"https://pith.science/api/pith-number/JAV2TP44UYWYPWVDVS4QLO4RC6/graph.json","events_json":"https://pith.science/api/pith-number/JAV2TP44UYWYPWVDVS4QLO4RC6/events.json","paper":"https://pith.science/paper/JAV2TP44"},"agent_actions":{"view_html":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6","download_json":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6.json","view_paper":"https://pith.science/paper/JAV2TP44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13073&json=true","fetch_graph":"https://pith.science/api/pith-number/JAV2TP44UYWYPWVDVS4QLO4RC6/graph.json","fetch_events":"https://pith.science/api/pith-number/JAV2TP44UYWYPWVDVS4QLO4RC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6/action/storage_attestation","attest_author":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6/action/author_attestation","sign_citation":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6/action/citation_signature","submit_replication":"https://pith.science/pith/JAV2TP44UYWYPWVDVS4QLO4RC6/action/replication_record"}},"created_at":"2026-07-05T02:51:40.620634+00:00","updated_at":"2026-07-05T02:51:40.620634+00:00"}