{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KX6JAJ6DCD5SNMRHNMVKIQLPGL","short_pith_number":"pith:KX6JAJ6D","schema_version":"1.0","canonical_sha256":"55fc9027c310fb26b2276b2aa4416f32cc9c733b1beaea2b449530517c99d893","source":{"kind":"arxiv","id":"2106.00188","version":2},"attestation_state":"computed","paper":{"title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Ari Holtzman, Matthew Peters, Roozbeh Mottaghi, Rowan Zellers, Yejin Choi","submitted_at":"2021-06-01T02:32:12Z","abstract_excerpt":"We propose PIGLeT: a model that learns physical commonsense knowledge through interaction, and then uses this knowledge to ground language. We factorize PIGLeT into a physical dynamics model, and a separate language model. Our dynamics model learns not just what objects are but also what they do: glass cups break when thrown, plastic ones don't. We then use it as the interface to our language model, giving us a unified model of linguistic form and grounded meaning. PIGLeT can read a sentence, simulate neurally what might happen next, and then communicate that result through a literal symbolic "},"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":"2106.00188","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T02:32:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9cce31814efd4ffac679a74610592f3db6c78c100baebcf8b38721c3b94edd0f","abstract_canon_sha256":"0575f925c341e3f5c06e8d58321afebaa061da0d5b186aa59d891f28c6379894"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:28.666696Z","signature_b64":"2alo2XISLW0FpQfkXSvBR7h2SfNmz3ucg5NkB5+MlJBec4BQS8bxQtPdcsDyRinoVOsUjO8ePRlrFeJ7fQB7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55fc9027c310fb26b2276b2aa4416f32cc9c733b1beaea2b449530517c99d893","last_reissued_at":"2026-07-05T03:52:28.666110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:28.666110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ali Farhadi, Aniruddha Kembhavi, Ari Holtzman, Matthew Peters, Roozbeh Mottaghi, Rowan Zellers, Yejin Choi","submitted_at":"2021-06-01T02:32:12Z","abstract_excerpt":"We propose PIGLeT: a model that learns physical commonsense knowledge through interaction, and then uses this knowledge to ground language. We factorize PIGLeT into a physical dynamics model, and a separate language model. Our dynamics model learns not just what objects are but also what they do: glass cups break when thrown, plastic ones don't. We then use it as the interface to our language model, giving us a unified model of linguistic form and grounded meaning. PIGLeT can read a sentence, simulate neurally what might happen next, and then communicate that result through a literal symbolic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00188","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/2106.00188/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":"2106.00188","created_at":"2026-07-05T03:52:28.666185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00188v2","created_at":"2026-07-05T03:52:28.666185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00188","created_at":"2026-07-05T03:52:28.666185+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX6JAJ6DCD5S","created_at":"2026-07-05T03:52:28.666185+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX6JAJ6DCD5SNMRH","created_at":"2026-07-05T03:52:28.666185+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX6JAJ6D","created_at":"2026-07-05T03:52:28.666185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL","json":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL.json","graph_json":"https://pith.science/api/pith-number/KX6JAJ6DCD5SNMRHNMVKIQLPGL/graph.json","events_json":"https://pith.science/api/pith-number/KX6JAJ6DCD5SNMRHNMVKIQLPGL/events.json","paper":"https://pith.science/paper/KX6JAJ6D"},"agent_actions":{"view_html":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL","download_json":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL.json","view_paper":"https://pith.science/paper/KX6JAJ6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00188&json=true","fetch_graph":"https://pith.science/api/pith-number/KX6JAJ6DCD5SNMRHNMVKIQLPGL/graph.json","fetch_events":"https://pith.science/api/pith-number/KX6JAJ6DCD5SNMRHNMVKIQLPGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL/action/storage_attestation","attest_author":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL/action/author_attestation","sign_citation":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL/action/citation_signature","submit_replication":"https://pith.science/pith/KX6JAJ6DCD5SNMRHNMVKIQLPGL/action/replication_record"}},"created_at":"2026-07-05T03:52:28.666185+00:00","updated_at":"2026-07-05T03:52:28.666185+00:00"}