{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PDKPA2N6WV4A5BLSALWCJDDPHO","short_pith_number":"pith:PDKPA2N6","schema_version":"1.0","canonical_sha256":"78d4f069beb5780e857202ec248c6f3bae710383f7e448e577128c86184ac68d","source":{"kind":"arxiv","id":"2107.08981","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Few-Shot Imitation with Skill Transition Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Albert Zhan, Kourosh Hakhamaneshi, Michael Laskin, Pieter Abbeel, Ruihan Zhao","submitted_at":"2021-07-19T15:56:01Z","abstract_excerpt":"A desirable property of autonomous agents is the ability to both solve long-horizon problems and generalize to unseen tasks. Recent advances in data-driven skill learning have shown that extracting behavioral priors from offline data can enable agents to solve challenging long-horizon tasks with reinforcement learning. However, generalization to tasks unseen during behavioral prior training remains an outstanding challenge. To this end, we present Few-shot Imitation with Skill Transition Models (FIST), an algorithm that extracts skills from offline data and utilizes them to generalize to unsee"},"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":"2107.08981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-19T15:56:01Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"2b4eab65cb282d24310caec51fabfb88c61e7431a0fbf525b5255a14d7a97e1f","abstract_canon_sha256":"af5d14083aee4418dc0a47a5162c255fe8662bff4dcc10dfd333834a37ec365c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:37.018488Z","signature_b64":"mcTd2NoQfg8f7wyVXJ8xDjKQZL/8FOn6p8ty+fZCi+q6mPJPyBBx/tA/ZeEutT+FUc9F7/pF6kZZIdBXaIZCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78d4f069beb5780e857202ec248c6f3bae710383f7e448e577128c86184ac68d","last_reissued_at":"2026-07-05T04:03:37.018013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:37.018013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Few-Shot Imitation with Skill Transition Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Albert Zhan, Kourosh Hakhamaneshi, Michael Laskin, Pieter Abbeel, Ruihan Zhao","submitted_at":"2021-07-19T15:56:01Z","abstract_excerpt":"A desirable property of autonomous agents is the ability to both solve long-horizon problems and generalize to unseen tasks. Recent advances in data-driven skill learning have shown that extracting behavioral priors from offline data can enable agents to solve challenging long-horizon tasks with reinforcement learning. However, generalization to tasks unseen during behavioral prior training remains an outstanding challenge. To this end, we present Few-shot Imitation with Skill Transition Models (FIST), an algorithm that extracts skills from offline data and utilizes them to generalize to unsee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08981","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/2107.08981/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":"2107.08981","created_at":"2026-07-05T04:03:37.018071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08981v2","created_at":"2026-07-05T04:03:37.018071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08981","created_at":"2026-07-05T04:03:37.018071+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDKPA2N6WV4A","created_at":"2026-07-05T04:03:37.018071+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDKPA2N6WV4A5BLS","created_at":"2026-07-05T04:03:37.018071+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDKPA2N6","created_at":"2026-07-05T04:03:37.018071+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/PDKPA2N6WV4A5BLSALWCJDDPHO","json":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO.json","graph_json":"https://pith.science/api/pith-number/PDKPA2N6WV4A5BLSALWCJDDPHO/graph.json","events_json":"https://pith.science/api/pith-number/PDKPA2N6WV4A5BLSALWCJDDPHO/events.json","paper":"https://pith.science/paper/PDKPA2N6"},"agent_actions":{"view_html":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO","download_json":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO.json","view_paper":"https://pith.science/paper/PDKPA2N6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08981&json=true","fetch_graph":"https://pith.science/api/pith-number/PDKPA2N6WV4A5BLSALWCJDDPHO/graph.json","fetch_events":"https://pith.science/api/pith-number/PDKPA2N6WV4A5BLSALWCJDDPHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO/action/storage_attestation","attest_author":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO/action/author_attestation","sign_citation":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO/action/citation_signature","submit_replication":"https://pith.science/pith/PDKPA2N6WV4A5BLSALWCJDDPHO/action/replication_record"}},"created_at":"2026-07-05T04:03:37.018071+00:00","updated_at":"2026-07-05T04:03:37.018071+00:00"}