{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DE2BXGU3MA5PBTJ2OCY443MJ77","short_pith_number":"pith:DE2BXGU3","schema_version":"1.0","canonical_sha256":"19341b9a9b603af0cd3a70b1ce6d89ffd9299d109053ef232700b9a98c6c1e15","source":{"kind":"arxiv","id":"1710.01813","version":2},"attestation_state":"computed","paper":{"title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Animesh Garg, Danfei Xu, Julian Gao, Li Fei-Fei, Silvio Savarese, Suraj Nair, Yuke Zhu","submitted_at":"2017-10-04T21:31:49Z","abstract_excerpt":"In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g., video demonstration of a task) and recursively decomposes it into finer sub-task specifications. These specifications are fed to a hierarchical neural program, where bottom-level programs are callable subroutines that interact with the environment. We validate our method in three robot manipulation tasks. NTP achieves strong generalization across sequential task"},"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":"1710.01813","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-04T21:31:49Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"74d72d24ee629f553ddd4eb00bb094545d801e9c324398839c9ba796c7535fdf","abstract_canon_sha256":"b41e8a60a5fd3a0d0442ee0355115630c15adfb60a1b060161d84dadd415dae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:56.167107Z","signature_b64":"k0TTRzZSOfhDfNyEqmTJuVV+Ux+do2dMv8p4NCjvtOUij6A401wegfyJzYq/HSFIiM42rasx9YLFlby6/VblDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19341b9a9b603af0cd3a70b1ce6d89ffd9299d109053ef232700b9a98c6c1e15","last_reissued_at":"2026-05-18T00:20:56.166583Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:56.166583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Animesh Garg, Danfei Xu, Julian Gao, Li Fei-Fei, Silvio Savarese, Suraj Nair, Yuke Zhu","submitted_at":"2017-10-04T21:31:49Z","abstract_excerpt":"In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g., video demonstration of a task) and recursively decomposes it into finer sub-task specifications. These specifications are fed to a hierarchical neural program, where bottom-level programs are callable subroutines that interact with the environment. We validate our method in three robot manipulation tasks. NTP achieves strong generalization across sequential task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01813","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":""},"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":"1710.01813","created_at":"2026-05-18T00:20:56.166657+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.01813v2","created_at":"2026-05-18T00:20:56.166657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01813","created_at":"2026-05-18T00:20:56.166657+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE2BXGU3MA5P","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE2BXGU3MA5PBTJ2","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE2BXGU3","created_at":"2026-05-18T12:31:10.602751+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/DE2BXGU3MA5PBTJ2OCY443MJ77","json":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77.json","graph_json":"https://pith.science/api/pith-number/DE2BXGU3MA5PBTJ2OCY443MJ77/graph.json","events_json":"https://pith.science/api/pith-number/DE2BXGU3MA5PBTJ2OCY443MJ77/events.json","paper":"https://pith.science/paper/DE2BXGU3"},"agent_actions":{"view_html":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77","download_json":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77.json","view_paper":"https://pith.science/paper/DE2BXGU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.01813&json=true","fetch_graph":"https://pith.science/api/pith-number/DE2BXGU3MA5PBTJ2OCY443MJ77/graph.json","fetch_events":"https://pith.science/api/pith-number/DE2BXGU3MA5PBTJ2OCY443MJ77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77/action/storage_attestation","attest_author":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77/action/author_attestation","sign_citation":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77/action/citation_signature","submit_replication":"https://pith.science/pith/DE2BXGU3MA5PBTJ2OCY443MJ77/action/replication_record"}},"created_at":"2026-05-18T00:20:56.166657+00:00","updated_at":"2026-05-18T00:20:56.166657+00:00"}