{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VSE6IW3LZPRUPIYXYY3KLS2XZX","short_pith_number":"pith:VSE6IW3L","schema_version":"1.0","canonical_sha256":"ac89e45b6bcbe347a317c636a5cb57cdc2a4999d05759b723a2b48faee59dfd3","source":{"kind":"arxiv","id":"1711.00482","version":1},"attestation_state":"computed","paper":{"title":"Learning with Latent Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Dan Klein, Jacob Andreas, Sergey Levine","submitted_at":"2017-11-01T18:00:22Z","abstract_excerpt":"The named concepts and compositional operators present in natural language provide a rich source of information about the kinds of abstractions humans use to navigate the world. Can this linguistic background knowledge improve the generality and efficiency of learned classifiers and control policies? This paper aims to show that using the space of natural language strings as a parameter space is an effective way to capture natural task structure. In a pretraining phase, we learn a language interpretation model that transforms inputs (e.g. images) into outputs (e.g. labels) given natural langua"},"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":"1711.00482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-01T18:00:22Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c9826aef0e7fe8486b36e4f4c0a229249483c03303e375aaf39aa4382ca49970","abstract_canon_sha256":"613f503bd15a7afeae450ead54c122c8dcdacc6cec092ab7ca86287c3e053c63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:30.504436Z","signature_b64":"dHM02Oy5BRKkn3qPX0sVqmu0FlsOxNRppOPEnvtCpzLK1334zbvnNOIaE03HPTNmNOVYXus5f22+EM32NqiAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac89e45b6bcbe347a317c636a5cb57cdc2a4999d05759b723a2b48faee59dfd3","last_reissued_at":"2026-05-18T00:31:30.503740Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:30.503740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Latent Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Dan Klein, Jacob Andreas, Sergey Levine","submitted_at":"2017-11-01T18:00:22Z","abstract_excerpt":"The named concepts and compositional operators present in natural language provide a rich source of information about the kinds of abstractions humans use to navigate the world. Can this linguistic background knowledge improve the generality and efficiency of learned classifiers and control policies? This paper aims to show that using the space of natural language strings as a parameter space is an effective way to capture natural task structure. In a pretraining phase, we learn a language interpretation model that transforms inputs (e.g. images) into outputs (e.g. labels) given natural langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00482","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":"1711.00482","created_at":"2026-05-18T00:31:30.503844+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00482v1","created_at":"2026-05-18T00:31:30.503844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00482","created_at":"2026-05-18T00:31:30.503844+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSE6IW3LZPRU","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSE6IW3LZPRUPIYX","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSE6IW3L","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2209.07753","citing_title":"Code as Policies: Language Model Programs for Embodied Control","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12412","citing_title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX","json":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX.json","graph_json":"https://pith.science/api/pith-number/VSE6IW3LZPRUPIYXYY3KLS2XZX/graph.json","events_json":"https://pith.science/api/pith-number/VSE6IW3LZPRUPIYXYY3KLS2XZX/events.json","paper":"https://pith.science/paper/VSE6IW3L"},"agent_actions":{"view_html":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX","download_json":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX.json","view_paper":"https://pith.science/paper/VSE6IW3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00482&json=true","fetch_graph":"https://pith.science/api/pith-number/VSE6IW3LZPRUPIYXYY3KLS2XZX/graph.json","fetch_events":"https://pith.science/api/pith-number/VSE6IW3LZPRUPIYXYY3KLS2XZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX/action/storage_attestation","attest_author":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX/action/author_attestation","sign_citation":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX/action/citation_signature","submit_replication":"https://pith.science/pith/VSE6IW3LZPRUPIYXYY3KLS2XZX/action/replication_record"}},"created_at":"2026-05-18T00:31:30.503844+00:00","updated_at":"2026-05-18T00:31:30.503844+00:00"}