{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XPUF42LI4ZS6VTUM7SWZSJLDRA","short_pith_number":"pith:XPUF42LI","schema_version":"1.0","canonical_sha256":"bbe85e6968e665eace8cfcad992563883ae21307b600e248ce04b4dcdac3eddf","source":{"kind":"arxiv","id":"1608.00272","version":3},"attestation_state":"computed","paper":{"title":"Modeling Context in Referring Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander C. Berg, Licheng Yu, Patrick Poirson, Shan Yang, Tamara L. Berg","submitted_at":"2016-07-31T22:21:42Z","abstract_excerpt":"Humans refer to objects in their environments all the time, especially in dialogue with other people. We explore generating and comprehending natural language referring expressions for objects in images. In particular, we focus on incorporating better measures of visual context into referring expression models and find that visual comparison to other objects within an image helps improve performance significantly. We also develop methods to tie the language generation process together, so that we generate expressions for all objects of a particular category jointly. Evaluation on three recent "},"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":"1608.00272","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-31T22:21:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"74d6803af20ea08fad116a61a1387fd37e96ece5d2dbf3179b87f0ad75f8dc0a","abstract_canon_sha256":"2c5befb3e84ce806f0cd84e5ebc850361d0734da435208b76c7991931caa158d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:30.652473Z","signature_b64":"x1JJtsxQVxu9gfwImZmssokrYfWS5mUEJ9oXkpiMAaOhA1BYu1U60kc7LP/mp9p3/SMjE1cPa8gdu0prL97aBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe85e6968e665eace8cfcad992563883ae21307b600e248ce04b4dcdac3eddf","last_reissued_at":"2026-05-18T01:09:30.652057Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:30.652057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Context in Referring Expressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander C. Berg, Licheng Yu, Patrick Poirson, Shan Yang, Tamara L. Berg","submitted_at":"2016-07-31T22:21:42Z","abstract_excerpt":"Humans refer to objects in their environments all the time, especially in dialogue with other people. We explore generating and comprehending natural language referring expressions for objects in images. In particular, we focus on incorporating better measures of visual context into referring expression models and find that visual comparison to other objects within an image helps improve performance significantly. We also develop methods to tie the language generation process together, so that we generate expressions for all objects of a particular category jointly. Evaluation on three recent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.00272","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1608.00272","created_at":"2026-05-18T01:09:30.652113+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.00272v3","created_at":"2026-05-18T01:09:30.652113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.00272","created_at":"2026-05-18T01:09:30.652113+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPUF42LI4ZS6","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPUF42LI4ZS6VTUM","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPUF42LI","created_at":"2026-05-18T12:30:51.357362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":140,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13310","citing_title":"Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2306.14824","citing_title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08962","citing_title":"MegaScale-Omni: A Hyper-Scale, Workload-Resilient System for MultiModal LLM Training in Production","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA","json":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA.json","graph_json":"https://pith.science/api/pith-number/XPUF42LI4ZS6VTUM7SWZSJLDRA/graph.json","events_json":"https://pith.science/api/pith-number/XPUF42LI4ZS6VTUM7SWZSJLDRA/events.json","paper":"https://pith.science/paper/XPUF42LI"},"agent_actions":{"view_html":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA","download_json":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA.json","view_paper":"https://pith.science/paper/XPUF42LI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.00272&json=true","fetch_graph":"https://pith.science/api/pith-number/XPUF42LI4ZS6VTUM7SWZSJLDRA/graph.json","fetch_events":"https://pith.science/api/pith-number/XPUF42LI4ZS6VTUM7SWZSJLDRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA/action/storage_attestation","attest_author":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA/action/author_attestation","sign_citation":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA/action/citation_signature","submit_replication":"https://pith.science/pith/XPUF42LI4ZS6VTUM7SWZSJLDRA/action/replication_record"}},"created_at":"2026-05-18T01:09:30.652113+00:00","updated_at":"2026-05-18T01:09:30.652113+00:00"}