{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VQJ3VEKTDN2P7D7ADWKKUN7EOH","short_pith_number":"pith:VQJ3VEKT","schema_version":"1.0","canonical_sha256":"ac13ba91531b74ff8fe01d94aa37e471ff296d43c9659c0b000d864a84ccd870","source":{"kind":"arxiv","id":"2110.01517","version":2},"attestation_state":"computed","paper":{"title":"Skill Induction and Planning with Latent Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Antonio Torralba, Jacob Andreas, Pratyusha Sharma","submitted_at":"2021-10-04T15:36:32Z","abstract_excerpt":"We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level subtasks, using only a small number of seed annotations to ground language in a"},"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":"2110.01517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T15:36:32Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"5c90c6dc4a6a734e7643f4136993a10d9721e6caca269e8b50ce1c0f63918d33","abstract_canon_sha256":"b62b52330bf711b9f18c9f73b62e7a0fd7bbfa7d06737a1a473e05eac7b060a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:22.422738Z","signature_b64":"ft2x8uyLyczk2GkYjpnnKFBcWbzDMuBzz3H2rbW+qgfmVtpe5Le6fgBBdK+BQfQ1m8pw5qT6wbzWePrt6FVeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac13ba91531b74ff8fe01d94aa37e471ff296d43c9659c0b000d864a84ccd870","last_reissued_at":"2026-07-05T04:19:22.422260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:22.422260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill Induction and Planning with Latent Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Antonio Torralba, Jacob Andreas, Pratyusha Sharma","submitted_at":"2021-10-04T15:36:32Z","abstract_excerpt":"We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model of action sequences in which goals generate sequences of high-level subtask descriptions, and these descriptions generate sequences of low-level actions. We describe how to train this model using primarily unannotated demonstrations by parsing demonstrations into sequences of named high-level subtasks, using only a small number of seed annotations to ground language in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01517","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/2110.01517/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":"2110.01517","created_at":"2026-07-05T04:19:22.422320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.01517v2","created_at":"2026-07-05T04:19:22.422320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01517","created_at":"2026-07-05T04:19:22.422320+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQJ3VEKTDN2P","created_at":"2026-07-05T04:19:22.422320+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQJ3VEKTDN2P7D7A","created_at":"2026-07-05T04:19:22.422320+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQJ3VEKT","created_at":"2026-07-05T04:19:22.422320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26239","citing_title":"Sentinel: Embodied Cooperative Spatial Reasoning and Planning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":292,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":32,"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":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH","json":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH.json","graph_json":"https://pith.science/api/pith-number/VQJ3VEKTDN2P7D7ADWKKUN7EOH/graph.json","events_json":"https://pith.science/api/pith-number/VQJ3VEKTDN2P7D7ADWKKUN7EOH/events.json","paper":"https://pith.science/paper/VQJ3VEKT"},"agent_actions":{"view_html":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH","download_json":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH.json","view_paper":"https://pith.science/paper/VQJ3VEKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.01517&json=true","fetch_graph":"https://pith.science/api/pith-number/VQJ3VEKTDN2P7D7ADWKKUN7EOH/graph.json","fetch_events":"https://pith.science/api/pith-number/VQJ3VEKTDN2P7D7ADWKKUN7EOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH/action/storage_attestation","attest_author":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH/action/author_attestation","sign_citation":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH/action/citation_signature","submit_replication":"https://pith.science/pith/VQJ3VEKTDN2P7D7ADWKKUN7EOH/action/replication_record"}},"created_at":"2026-07-05T04:19:22.422320+00:00","updated_at":"2026-07-05T04:19:22.422320+00:00"}