{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z25N2QHEMGUFMNOLGK263S3ZCI","short_pith_number":"pith:Z25N2QHE","schema_version":"1.0","canonical_sha256":"cebadd40e461a85635cb32b5edcb791206ea19f60b390f0926ba2f3cf18de1f6","source":{"kind":"arxiv","id":"1910.10628","version":2},"attestation_state":"computed","paper":{"title":"Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aaron Gokaslan, Daniel Nikovski, Devesh Jha, Diego Romeres, George Konidaris, Jonathan Chang, Nishanth Kumar, Sean Hastings, Stefanie Tellex","submitted_at":"2019-10-23T15:54:32Z","abstract_excerpt":"Robots need to learn skills that can not only generalize across similar problems but also be directed to a specific goal. Previous methods either train a new skill for every different goal or do not infer the specific target in the presence of multiple goals from visual data. We introduce an end-to-end method that represents targetable visuomotor skills as a goal-parameterized neural network policy. By training on an informative subset of available goals with the associated target parameters, we are able to learn a policy that can zero-shot generalize to previously unseen goals. We evaluate ou"},"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":"1910.10628","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2019-10-23T15:54:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ffa702ac59c3037ac5c7fa20276018e4c2edd6b1060ed2e66eb922cd2ab1b1f7","abstract_canon_sha256":"279bddafb88d0ac9354ea5acc7711e4bb7b35475b615423debf48217d976eefd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:49.494273Z","signature_b64":"ZYcBIM8DleJl+hNbYBHcGlsqxBbLP5KHDd6h10NTYGtiH3LapXZYt6IuTztAOsGJHv3IpC4OXmT/ZLlrscUNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cebadd40e461a85635cb32b5edcb791206ea19f60b390f0926ba2f3cf18de1f6","last_reissued_at":"2026-07-05T02:18:49.493863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:49.493863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aaron Gokaslan, Daniel Nikovski, Devesh Jha, Diego Romeres, George Konidaris, Jonathan Chang, Nishanth Kumar, Sean Hastings, Stefanie Tellex","submitted_at":"2019-10-23T15:54:32Z","abstract_excerpt":"Robots need to learn skills that can not only generalize across similar problems but also be directed to a specific goal. Previous methods either train a new skill for every different goal or do not infer the specific target in the presence of multiple goals from visual data. We introduce an end-to-end method that represents targetable visuomotor skills as a goal-parameterized neural network policy. By training on an informative subset of available goals with the associated target parameters, we are able to learn a policy that can zero-shot generalize to previously unseen goals. We evaluate ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10628","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/1910.10628/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":"1910.10628","created_at":"2026-07-05T02:18:49.493922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.10628v2","created_at":"2026-07-05T02:18:49.493922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10628","created_at":"2026-07-05T02:18:49.493922+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z25N2QHEMGUF","created_at":"2026-07-05T02:18:49.493922+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z25N2QHEMGUFMNOL","created_at":"2026-07-05T02:18:49.493922+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z25N2QHE","created_at":"2026-07-05T02:18:49.493922+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/Z25N2QHEMGUFMNOLGK263S3ZCI","json":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI.json","graph_json":"https://pith.science/api/pith-number/Z25N2QHEMGUFMNOLGK263S3ZCI/graph.json","events_json":"https://pith.science/api/pith-number/Z25N2QHEMGUFMNOLGK263S3ZCI/events.json","paper":"https://pith.science/paper/Z25N2QHE"},"agent_actions":{"view_html":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI","download_json":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI.json","view_paper":"https://pith.science/paper/Z25N2QHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.10628&json=true","fetch_graph":"https://pith.science/api/pith-number/Z25N2QHEMGUFMNOLGK263S3ZCI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z25N2QHEMGUFMNOLGK263S3ZCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI/action/storage_attestation","attest_author":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI/action/author_attestation","sign_citation":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI/action/citation_signature","submit_replication":"https://pith.science/pith/Z25N2QHEMGUFMNOLGK263S3ZCI/action/replication_record"}},"created_at":"2026-07-05T02:18:49.493922+00:00","updated_at":"2026-07-05T02:18:49.493922+00:00"}