{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JAV2TP44UYWYPWVDVS4QLO4RC6","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":"3c94efdada60f33b6b6831f9f769a85d818f16c001224c9ba5732eaf754268d2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T11:45:29Z","title_canon_sha256":"e78c6b1bb13cb9315ad1f6da36f9688791a03e77a32fb681a593068835f83fc3"},"schema_version":"1.0","source":{"id":"2105.13073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13073","created_at":"2026-07-05T02:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13073v2","created_at":"2026-07-05T02:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13073","created_at":"2026-07-05T02:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"JAV2TP44UYWY","created_at":"2026-07-05T02:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"JAV2TP44UYWYPWVD","created_at":"2026-07-05T02:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"JAV2TP44","created_at":"2026-07-05T02:51:40Z"}],"graph_snapshots":[{"event_id":"sha256:3df19946846b7e0f021bec97f37a6e8aa301196eb436c076dd74932403fe619a","target":"graph","created_at":"2026-07-05T02:51:40Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.13073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Fan Liang, Huang Hu, Xiubo Geng, Yining Chen, Zujie Liang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T11:45:29Z","title":"Maria: A Visual Experience Powered Conversational Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13073","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":"sha256:8f91c6f5520576239f547e2085f057fa8dd642d65d47d9b1a16b1dc816ec1ace","target":"record","created_at":"2026-07-05T02:51:40Z","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":"3c94efdada60f33b6b6831f9f769a85d818f16c001224c9ba5732eaf754268d2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-27T11:45:29Z","title_canon_sha256":"e78c6b1bb13cb9315ad1f6da36f9688791a03e77a32fb681a593068835f83fc3"},"schema_version":"1.0","source":{"id":"2105.13073","kind":"arxiv","version":2}},"canonical_sha256":"482ba9bf9ca62d87daa3acb905bb9117ac290a1fd0cc048f0c92be2288c82604","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"482ba9bf9ca62d87daa3acb905bb9117ac290a1fd0cc048f0c92be2288c82604","first_computed_at":"2026-07-05T02:51:40.620576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:51:40.620576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4M9mBQOUhEvXBQ6Hq1DGY2yRt+3/Frb/D53GNnwiC2qbVhSDPbGcS7qTvVzJFq0zPsEBGZxnoLjroflXoK+TDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:51:40.621123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f91c6f5520576239f547e2085f057fa8dd642d65d47d9b1a16b1dc816ec1ace","sha256:3df19946846b7e0f021bec97f37a6e8aa301196eb436c076dd74932403fe619a"],"state_sha256":"7a8dba241c12fa0739767dbed68e57aa3d00c3cbdb2a74a141c2b470ff94ad53"}