{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PPH3L5TPR6OMHA46JJNAXIMANS","short_pith_number":"pith:PPH3L5TP","schema_version":"1.0","canonical_sha256":"7bcfb5f66f8f9cc3839e4a5a0ba1806ca35fd92dc6f7c6b3823d943d51f192f7","source":{"kind":"arxiv","id":"2011.05970","version":1},"attestation_state":"computed","paper":{"title":"Transformers for One-Shot Visual Imitation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Sudeep Dasari","submitted_at":"2020-11-11T18:41:07Z","abstract_excerpt":"Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate that into concrete motor control. Is it possible to give a robot this same capability? Prior research in robot imitation learning has created agents which can acquire diverse skills from expert human operators. However, expanding these techniques to work with a single positive example during test time is still an open challenge. Apart from control, the difficu"},"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":"2011.05970","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T18:41:07Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"6df4ec60bfcea827fc09f5bac42387c75e4c58d1990b1ecdfaa7348de0f1a178","abstract_canon_sha256":"9880e2f0c69eb68642d25d2cfd6272289d857df3b6fcf954ca4d1dd53d6ae7b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:03.270078Z","signature_b64":"SGSm6AoDnqPe6SlzrQac+BDnjDUDd/haYaff1vORJk75/fPszKfb/H+9u5ZZbnS5oqTiE8/hVkw8or1Zrn+TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bcfb5f66f8f9cc3839e4a5a0ba1806ca35fd92dc6f7c6b3823d943d51f192f7","last_reissued_at":"2026-07-05T01:51:03.269600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:03.269600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers for One-Shot Visual Imitation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhinav Gupta, Sudeep Dasari","submitted_at":"2020-11-11T18:41:07Z","abstract_excerpt":"Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate that into concrete motor control. Is it possible to give a robot this same capability? Prior research in robot imitation learning has created agents which can acquire diverse skills from expert human operators. However, expanding these techniques to work with a single positive example during test time is still an open challenge. Apart from control, the difficu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05970","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/2011.05970/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":"2011.05970","created_at":"2026-07-05T01:51:03.269653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05970v1","created_at":"2026-07-05T01:51:03.269653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05970","created_at":"2026-07-05T01:51:03.269653+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPH3L5TPR6OM","created_at":"2026-07-05T01:51:03.269653+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPH3L5TPR6OMHA46","created_at":"2026-07-05T01:51:03.269653+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPH3L5TP","created_at":"2026-07-05T01:51:03.269653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2106.01345","citing_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS","json":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS.json","graph_json":"https://pith.science/api/pith-number/PPH3L5TPR6OMHA46JJNAXIMANS/graph.json","events_json":"https://pith.science/api/pith-number/PPH3L5TPR6OMHA46JJNAXIMANS/events.json","paper":"https://pith.science/paper/PPH3L5TP"},"agent_actions":{"view_html":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS","download_json":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS.json","view_paper":"https://pith.science/paper/PPH3L5TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05970&json=true","fetch_graph":"https://pith.science/api/pith-number/PPH3L5TPR6OMHA46JJNAXIMANS/graph.json","fetch_events":"https://pith.science/api/pith-number/PPH3L5TPR6OMHA46JJNAXIMANS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS/action/storage_attestation","attest_author":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS/action/author_attestation","sign_citation":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS/action/citation_signature","submit_replication":"https://pith.science/pith/PPH3L5TPR6OMHA46JJNAXIMANS/action/replication_record"}},"created_at":"2026-07-05T01:51:03.269653+00:00","updated_at":"2026-07-05T01:51:03.269653+00:00"}