{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:77E3YIFYNK35CO4QIHLQBLLXQU","short_pith_number":"pith:77E3YIFY","schema_version":"1.0","canonical_sha256":"ffc9bc20b86ab7d13b9041d700ad778508d7074f04c098b1b91b08c301926ec2","source":{"kind":"arxiv","id":"1909.00421","version":1},"attestation_state":"computed","paper":{"title":"What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changshui Zhang, Hongming Zhang, Xintong Yu, Yangqiu Song, Yan Song","submitted_at":"2019-09-01T15:47:03Z","abstract_excerpt":"Grounding a pronoun to a visual object it refers to requires complex reasoning from various information sources, especially in conversational scenarios. For example, when people in a conversation talk about something all speakers can see, they often directly use pronouns (e.g., it) to refer to it without previous introduction. This fact brings a huge challenge for modern natural language understanding systems, particularly conventional context-based pronoun coreference models. To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (P"},"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":"1909.00421","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-01T15:47:03Z","cross_cats_sorted":[],"title_canon_sha256":"d63ada571ace54ebc21ed52a23154ed6b3f4d3a0c564852fe88be8260d3eca03","abstract_canon_sha256":"c25152c41dab9c6c79d128cb3fa4ec16fef5e122adf20bd5518a335331b50f82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:08.971931Z","signature_b64":"4ppEwCwWDQeQyUY/HgSx1l00USdC7JdeBsvAAi9LMTFzegQYTvc9ueKfnTsnfvwJglIDlYC9mRRhlDWHIfsUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffc9bc20b86ab7d13b9041d700ad778508d7074f04c098b1b91b08c301926ec2","last_reissued_at":"2026-07-05T00:01:08.971454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:08.971454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changshui Zhang, Hongming Zhang, Xintong Yu, Yangqiu Song, Yan Song","submitted_at":"2019-09-01T15:47:03Z","abstract_excerpt":"Grounding a pronoun to a visual object it refers to requires complex reasoning from various information sources, especially in conversational scenarios. For example, when people in a conversation talk about something all speakers can see, they often directly use pronouns (e.g., it) to refer to it without previous introduction. This fact brings a huge challenge for modern natural language understanding systems, particularly conventional context-based pronoun coreference models. To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00421","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/1909.00421/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":"1909.00421","created_at":"2026-07-05T00:01:08.971515+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00421v1","created_at":"2026-07-05T00:01:08.971515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00421","created_at":"2026-07-05T00:01:08.971515+00:00"},{"alias_kind":"pith_short_12","alias_value":"77E3YIFYNK35","created_at":"2026-07-05T00:01:08.971515+00:00"},{"alias_kind":"pith_short_16","alias_value":"77E3YIFYNK35CO4Q","created_at":"2026-07-05T00:01:08.971515+00:00"},{"alias_kind":"pith_short_8","alias_value":"77E3YIFY","created_at":"2026-07-05T00:01:08.971515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.02791","citing_title":"Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU","json":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU.json","graph_json":"https://pith.science/api/pith-number/77E3YIFYNK35CO4QIHLQBLLXQU/graph.json","events_json":"https://pith.science/api/pith-number/77E3YIFYNK35CO4QIHLQBLLXQU/events.json","paper":"https://pith.science/paper/77E3YIFY"},"agent_actions":{"view_html":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU","download_json":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU.json","view_paper":"https://pith.science/paper/77E3YIFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00421&json=true","fetch_graph":"https://pith.science/api/pith-number/77E3YIFYNK35CO4QIHLQBLLXQU/graph.json","fetch_events":"https://pith.science/api/pith-number/77E3YIFYNK35CO4QIHLQBLLXQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU/action/storage_attestation","attest_author":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU/action/author_attestation","sign_citation":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU/action/citation_signature","submit_replication":"https://pith.science/pith/77E3YIFYNK35CO4QIHLQBLLXQU/action/replication_record"}},"created_at":"2026-07-05T00:01:08.971515+00:00","updated_at":"2026-07-05T00:01:08.971515+00:00"}