{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:55MXVZSH23XGUKSFRSFICCI4AC","short_pith_number":"pith:55MXVZSH","schema_version":"1.0","canonical_sha256":"ef597ae647d6ee6a2a458c8a81091c00ba2dfc8ea3772aace6425928405a026d","source":{"kind":"arxiv","id":"2303.01497","version":1},"attestation_state":"computed","paper":{"title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anant Rai, Jyothish Pari, Lerrel Pinto, Siddhant Haldar","submitted_at":"2023-03-02T18:57:38Z","abstract_excerpt":"While imitation learning provides us with an efficient toolkit to train robots, learning skills that are robust to environment variations remains a significant challenge. Current approaches address this challenge by relying either on large amounts of demonstrations that span environment variations or on handcrafted reward functions that require state estimates. Both directions are not scalable to fast imitation. In this work, we present Fast Imitation of Skills from Humans (FISH), a new imitation learning approach that can learn robust visual skills with less than a minute of human demonstrati"},"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":"2303.01497","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2023-03-02T18:57:38Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d10a03e633924fa158f0ab31fff7b46348af114374d974ae0b4f2866307c7999","abstract_canon_sha256":"0bdb22203ed19849025b3d6f482dc152efd4df27470d46703235045522e2b466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:31.899283Z","signature_b64":"NE2C9QOU3EpSzFCf/lRfmohCGHeNZ+Se5J7KDzQct2y1Af3KOrexXDDOU3uHV7cfzr8TrPwrE474uKRarxBvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef597ae647d6ee6a2a458c8a81091c00ba2dfc8ea3772aace6425928405a026d","last_reissued_at":"2026-07-05T05:47:31.898875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:31.898875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Anant Rai, Jyothish Pari, Lerrel Pinto, Siddhant Haldar","submitted_at":"2023-03-02T18:57:38Z","abstract_excerpt":"While imitation learning provides us with an efficient toolkit to train robots, learning skills that are robust to environment variations remains a significant challenge. Current approaches address this challenge by relying either on large amounts of demonstrations that span environment variations or on handcrafted reward functions that require state estimates. Both directions are not scalable to fast imitation. In this work, we present Fast Imitation of Skills from Humans (FISH), a new imitation learning approach that can learn robust visual skills with less than a minute of human demonstrati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01497","kind":"arxiv","version":1},"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/2303.01497/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":"2303.01497","created_at":"2026-07-05T05:47:31.898932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01497v1","created_at":"2026-07-05T05:47:31.898932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01497","created_at":"2026-07-05T05:47:31.898932+00:00"},{"alias_kind":"pith_short_12","alias_value":"55MXVZSH23XG","created_at":"2026-07-05T05:47:31.898932+00:00"},{"alias_kind":"pith_short_16","alias_value":"55MXVZSH23XGUKSF","created_at":"2026-07-05T05:47:31.898932+00:00"},{"alias_kind":"pith_short_8","alias_value":"55MXVZSH","created_at":"2026-07-05T05:47:31.898932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08828","citing_title":"Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08555","citing_title":"FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2409.00588","citing_title":"Diffusion Policy Policy Optimization","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05544","citing_title":"Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC","json":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC.json","graph_json":"https://pith.science/api/pith-number/55MXVZSH23XGUKSFRSFICCI4AC/graph.json","events_json":"https://pith.science/api/pith-number/55MXVZSH23XGUKSFRSFICCI4AC/events.json","paper":"https://pith.science/paper/55MXVZSH"},"agent_actions":{"view_html":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC","download_json":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC.json","view_paper":"https://pith.science/paper/55MXVZSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01497&json=true","fetch_graph":"https://pith.science/api/pith-number/55MXVZSH23XGUKSFRSFICCI4AC/graph.json","fetch_events":"https://pith.science/api/pith-number/55MXVZSH23XGUKSFRSFICCI4AC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC/action/storage_attestation","attest_author":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC/action/author_attestation","sign_citation":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC/action/citation_signature","submit_replication":"https://pith.science/pith/55MXVZSH23XGUKSFRSFICCI4AC/action/replication_record"}},"created_at":"2026-07-05T05:47:31.898932+00:00","updated_at":"2026-07-05T05:47:31.898932+00:00"}