{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:77E3YIFYNK35CO4QIHLQBLLXQU","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":"c25152c41dab9c6c79d128cb3fa4ec16fef5e122adf20bd5518a335331b50f82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-01T15:47:03Z","title_canon_sha256":"d63ada571ace54ebc21ed52a23154ed6b3f4d3a0c564852fe88be8260d3eca03"},"schema_version":"1.0","source":{"id":"1909.00421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00421","created_at":"2026-07-05T00:01:08Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00421v1","created_at":"2026-07-05T00:01:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00421","created_at":"2026-07-05T00:01:08Z"},{"alias_kind":"pith_short_12","alias_value":"77E3YIFYNK35","created_at":"2026-07-05T00:01:08Z"},{"alias_kind":"pith_short_16","alias_value":"77E3YIFYNK35CO4Q","created_at":"2026-07-05T00:01:08Z"},{"alias_kind":"pith_short_8","alias_value":"77E3YIFY","created_at":"2026-07-05T00:01:08Z"}],"graph_snapshots":[{"event_id":"sha256:3470f80e667158bcdf58798386b5578cc279b2aaee30f2cae34b7b2e809a348f","target":"graph","created_at":"2026-07-05T00:01:08Z","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/1909.00421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changshui Zhang, Hongming Zhang, Xintong Yu, Yangqiu Song, Yan Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-01T15:47:03Z","title":"What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00421","kind":"arxiv","version":1},"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":"sha256:15f48f3c7d4d62286831633cb6167cad1d23fbf632b59ea4f298d34eea0830da","target":"record","created_at":"2026-07-05T00:01:08Z","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":"c25152c41dab9c6c79d128cb3fa4ec16fef5e122adf20bd5518a335331b50f82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-01T15:47:03Z","title_canon_sha256":"d63ada571ace54ebc21ed52a23154ed6b3f4d3a0c564852fe88be8260d3eca03"},"schema_version":"1.0","source":{"id":"1909.00421","kind":"arxiv","version":1}},"canonical_sha256":"ffc9bc20b86ab7d13b9041d700ad778508d7074f04c098b1b91b08c301926ec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffc9bc20b86ab7d13b9041d700ad778508d7074f04c098b1b91b08c301926ec2","first_computed_at":"2026-07-05T00:01:08.971454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:01:08.971454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ppEwCwWDQeQyUY/HgSx1l00USdC7JdeBsvAAi9LMTFzegQYTvc9ueKfnTsnfvwJglIDlYC9mRRhlDWHIfsUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:01:08.971931Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15f48f3c7d4d62286831633cb6167cad1d23fbf632b59ea4f298d34eea0830da","sha256:3470f80e667158bcdf58798386b5578cc279b2aaee30f2cae34b7b2e809a348f"],"state_sha256":"cb29069d402cae4ee6b4c9fe4aebf4b8592fbc8ec215332b289c5dd496a00d38"}