{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7TH7DWH46Q2GPLEJGFUBJRCO2O","short_pith_number":"pith:7TH7DWH4","schema_version":"1.0","canonical_sha256":"fccff1d8fcf43467ac89316814c44ed3b8ac985dee9303a2564c99fedafa1c7e","source":{"kind":"arxiv","id":"2308.01399","version":2},"attestation_state":"computed","paper":{"title":"Learning to Model the World with Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anca Dragan, Danijar Hafner, Dan Klein, Jessy Lin, Olivia Watkins, Pieter Abbeel, Yuqing Du","submitted_at":"2023-07-31T17:57:49Z","abstract_excerpt":"To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language -- language like \"this button turns on the TV\" or \"I put the bowls away\" -- that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future: what they will observe, how the"},"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":"2308.01399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-31T17:57:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58bea088bf002c9fb3c2511ddde41103ed3a800b13f7ade81e3321335cf347ef","abstract_canon_sha256":"4aa48b0c489b69c8a975e879914e7aed7592c0701373b1f7d1c21f3e2682eed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:28.269077Z","signature_b64":"wK0HmX8QVk127N3MfVLm77XCbgd/hPxCknIGsXb7DG6QN84J6GtV8C7MiAx49gGP8QOX+yIutTCkhMJopbpJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fccff1d8fcf43467ac89316814c44ed3b8ac985dee9303a2564c99fedafa1c7e","last_reissued_at":"2026-07-05T08:25:28.268679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:28.268679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Model the World with Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anca Dragan, Danijar Hafner, Dan Klein, Jessy Lin, Olivia Watkins, Pieter Abbeel, Yuqing Du","submitted_at":"2023-07-31T17:57:49Z","abstract_excerpt":"To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language -- language like \"this button turns on the TV\" or \"I put the bowls away\" -- that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future: what they will observe, how the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01399","kind":"arxiv","version":2},"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/2308.01399/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":"2308.01399","created_at":"2026-07-05T08:25:28.268737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01399v2","created_at":"2026-07-05T08:25:28.268737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01399","created_at":"2026-07-05T08:25:28.268737+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TH7DWH46Q2G","created_at":"2026-07-05T08:25:28.268737+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TH7DWH46Q2GPLEJ","created_at":"2026-07-05T08:25:28.268737+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TH7DWH4","created_at":"2026-07-05T08:25:28.268737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24669","citing_title":"LaGO: Latent Action Guidance for Online Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30346","citing_title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O","json":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O.json","graph_json":"https://pith.science/api/pith-number/7TH7DWH46Q2GPLEJGFUBJRCO2O/graph.json","events_json":"https://pith.science/api/pith-number/7TH7DWH46Q2GPLEJGFUBJRCO2O/events.json","paper":"https://pith.science/paper/7TH7DWH4"},"agent_actions":{"view_html":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O","download_json":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O.json","view_paper":"https://pith.science/paper/7TH7DWH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01399&json=true","fetch_graph":"https://pith.science/api/pith-number/7TH7DWH46Q2GPLEJGFUBJRCO2O/graph.json","fetch_events":"https://pith.science/api/pith-number/7TH7DWH46Q2GPLEJGFUBJRCO2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O/action/storage_attestation","attest_author":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O/action/author_attestation","sign_citation":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O/action/citation_signature","submit_replication":"https://pith.science/pith/7TH7DWH46Q2GPLEJGFUBJRCO2O/action/replication_record"}},"created_at":"2026-07-05T08:25:28.268737+00:00","updated_at":"2026-07-05T08:25:28.268737+00:00"}