{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JDSU755M3L6AWHSNYBVU6ONJCY","short_pith_number":"pith:JDSU755M","schema_version":"1.0","canonical_sha256":"48e54ff7acdafc0b1e4dc06b4f39a91627bd81840a9b8bb459297b6442bea0d9","source":{"kind":"arxiv","id":"2007.14987","version":4},"attestation_state":"computed","paper":{"title":"Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.RO","authors_text":"Cynthia Matuszek, Don Engel, Edward Raff, Francis Ferraro, Gaoussou Youssouf Kebe, John Winder, Kasra Darvish, Padraig Higgins, Patrick Jenkins, Rishabh Sachdeva","submitted_at":"2020-07-29T17:58:04Z","abstract_excerpt":"Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI. In practice the data used for learning consists almost entirely of textual descriptions, which tend to be cleaner, clearer, and more grammatical than actual human interactions. In this work, we present the Grounded Language Dataset (GoLD), a multimodal dataset of common household objects described by people using either spoken or written language. We analyze the differences and present an experiment showing how the different modalitie"},"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":"2007.14987","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-07-29T17:58:04Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"b7f25cd980c740dc0e310dc95358e55fde97c44bf1d0e3b5580e654e0841e8b9","abstract_canon_sha256":"514b60bb0bbe2e958a09f15724d8a2f0bdda8813e87f2787f69beb2c78b1280b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:19.965065Z","signature_b64":"o8vpDVzl6A/N4X/AX+5hJ2XNM6vpYtH/7bCXj9ojUMpFQ1BnQtYYmCvTSGBcZs5btbLkGBNVQQZoLKpaAlu5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48e54ff7acdafc0b1e4dc06b4f39a91627bd81840a9b8bb459297b6442bea0d9","last_reissued_at":"2026-07-05T01:38:19.964696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:19.964696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.RO","authors_text":"Cynthia Matuszek, Don Engel, Edward Raff, Francis Ferraro, Gaoussou Youssouf Kebe, John Winder, Kasra Darvish, Padraig Higgins, Patrick Jenkins, Rishabh Sachdeva","submitted_at":"2020-07-29T17:58:04Z","abstract_excerpt":"Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI. In practice the data used for learning consists almost entirely of textual descriptions, which tend to be cleaner, clearer, and more grammatical than actual human interactions. In this work, we present the Grounded Language Dataset (GoLD), a multimodal dataset of common household objects described by people using either spoken or written language. We analyze the differences and present an experiment showing how the different modalitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14987","kind":"arxiv","version":4},"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/2007.14987/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":"2007.14987","created_at":"2026-07-05T01:38:19.964755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.14987v4","created_at":"2026-07-05T01:38:19.964755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14987","created_at":"2026-07-05T01:38:19.964755+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDSU755M3L6A","created_at":"2026-07-05T01:38:19.964755+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDSU755M3L6AWHSN","created_at":"2026-07-05T01:38:19.964755+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDSU755M","created_at":"2026-07-05T01:38:19.964755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY","json":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY.json","graph_json":"https://pith.science/api/pith-number/JDSU755M3L6AWHSNYBVU6ONJCY/graph.json","events_json":"https://pith.science/api/pith-number/JDSU755M3L6AWHSNYBVU6ONJCY/events.json","paper":"https://pith.science/paper/JDSU755M"},"agent_actions":{"view_html":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY","download_json":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY.json","view_paper":"https://pith.science/paper/JDSU755M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.14987&json=true","fetch_graph":"https://pith.science/api/pith-number/JDSU755M3L6AWHSNYBVU6ONJCY/graph.json","fetch_events":"https://pith.science/api/pith-number/JDSU755M3L6AWHSNYBVU6ONJCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY/action/storage_attestation","attest_author":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY/action/author_attestation","sign_citation":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY/action/citation_signature","submit_replication":"https://pith.science/pith/JDSU755M3L6AWHSNYBVU6ONJCY/action/replication_record"}},"created_at":"2026-07-05T01:38:19.964755+00:00","updated_at":"2026-07-05T01:38:19.964755+00:00"}