{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SA5MJPF5JSLQ6L3V6KKVV5LRRR","short_pith_number":"pith:SA5MJPF5","schema_version":"1.0","canonical_sha256":"903ac4bcbd4c970f2f75f2955af5718c5da5ced38a9ba19e36cb8cc44199665b","source":{"kind":"arxiv","id":"1603.08079","version":1},"attestation_state":"computed","paper":{"title":"Do You See What I Mean? Visual Resolution of Linguistic Ambiguities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrei Barbu, Boris Katz, Daniel Harari, Shimon Ullman, Yevgeni Berzak","submitted_at":"2016-03-26T06:49:33Z","abstract_excerpt":"Understanding language goes hand in hand with the ability to integrate complex contextual information obtained via perception. In this work, we present a novel task for grounded language understanding: disambiguating a sentence given a visual scene which depicts one of the possible interpretations of that sentence. To this end, we introduce a new multimodal corpus containing ambiguous sentences, representing a wide range of syntactic, semantic and discourse ambiguities, coupled with videos that visualize the different interpretations for each sentence. We address this task by extending a visio"},"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":"1603.08079","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-26T06:49:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1f4703efa60c6e4affff63bd0a39b75865686e9c7a6d53de37c4e169b8e19520","abstract_canon_sha256":"a698af399c85ead8df5a14350dd39f051ff54fc40f9a12a3f97fad57f9ab6c99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:46.721174Z","signature_b64":"lmCUu9PRJ4jAKCXD7B74i3pIb/AZXJYf2LhC8424YGLx7b2oXAKzGzeR+3/6DUDqQKSFRBatVlOhC59m8tFbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"903ac4bcbd4c970f2f75f2955af5718c5da5ced38a9ba19e36cb8cc44199665b","last_reissued_at":"2026-05-18T01:17:46.720530Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:46.720530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do You See What I Mean? Visual Resolution of Linguistic Ambiguities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrei Barbu, Boris Katz, Daniel Harari, Shimon Ullman, Yevgeni Berzak","submitted_at":"2016-03-26T06:49:33Z","abstract_excerpt":"Understanding language goes hand in hand with the ability to integrate complex contextual information obtained via perception. In this work, we present a novel task for grounded language understanding: disambiguating a sentence given a visual scene which depicts one of the possible interpretations of that sentence. To this end, we introduce a new multimodal corpus containing ambiguous sentences, representing a wide range of syntactic, semantic and discourse ambiguities, coupled with videos that visualize the different interpretations for each sentence. We address this task by extending a visio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08079","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":""},"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":"1603.08079","created_at":"2026-05-18T01:17:46.720614+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.08079v1","created_at":"2026-05-18T01:17:46.720614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08079","created_at":"2026-05-18T01:17:46.720614+00:00"},{"alias_kind":"pith_short_12","alias_value":"SA5MJPF5JSLQ","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SA5MJPF5JSLQ6L3V","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SA5MJPF5","created_at":"2026-05-18T12:30:44.179134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR","json":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR.json","graph_json":"https://pith.science/api/pith-number/SA5MJPF5JSLQ6L3V6KKVV5LRRR/graph.json","events_json":"https://pith.science/api/pith-number/SA5MJPF5JSLQ6L3V6KKVV5LRRR/events.json","paper":"https://pith.science/paper/SA5MJPF5"},"agent_actions":{"view_html":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR","download_json":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR.json","view_paper":"https://pith.science/paper/SA5MJPF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.08079&json=true","fetch_graph":"https://pith.science/api/pith-number/SA5MJPF5JSLQ6L3V6KKVV5LRRR/graph.json","fetch_events":"https://pith.science/api/pith-number/SA5MJPF5JSLQ6L3V6KKVV5LRRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR/action/storage_attestation","attest_author":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR/action/author_attestation","sign_citation":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR/action/citation_signature","submit_replication":"https://pith.science/pith/SA5MJPF5JSLQ6L3V6KKVV5LRRR/action/replication_record"}},"created_at":"2026-05-18T01:17:46.720614+00:00","updated_at":"2026-05-18T01:17:46.720614+00:00"}