{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AKCUZQYZVBEBWJY467VYTFOWBP","short_pith_number":"pith:AKCUZQYZ","schema_version":"1.0","canonical_sha256":"02854cc319a8481b271cf7eb8995d60be5dc7db7311b932cc7e4f37249f386c8","source":{"kind":"arxiv","id":"2412.10778","version":2},"attestation_state":"computed","paper":{"title":"Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoran Li, Xin Liu, Yaran Chen","submitted_at":"2024-12-14T10:12:22Z","abstract_excerpt":"Current advanced policy learning methodologies have demonstrated the ability to develop expert-level strategies when provided enough information. However, their requirements, including task-specific rewards, action-labeled expert trajectories, and huge environmental interactions, can be expensive or even unavailable in many scenarios. In contrast, humans can efficiently acquire skills within a few trials and errors by imitating easily accessible internet videos, in the absence of any other supervision. In this paper, we try to let machines replicate this efficient watching-and-learning process"},"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":"2412.10778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T10:12:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"342d423e80b8befbec89d53cbf1674fb5474449c4a94cfd95c75ef5e7f9f581e","abstract_canon_sha256":"5015342f55ddb9ff9e69c9ff09128b8368ae89cd1afef49119bd7e1328626ea4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:58.370238Z","signature_b64":"Y4zNteJuvgobH5lWhrqIjy6ZK49Gr6mb3L/Uy+DersoR/A+iCABTSHuIy2T9x/b85t5YgmLqc0ymbsZs/NakBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02854cc319a8481b271cf7eb8995d60be5dc7db7311b932cc7e4f37249f386c8","last_reissued_at":"2026-07-05T10:45:58.369642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:58.369642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-efficient Unsupervised Policy Cloning from Ensemble Self-supervised Labeled Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoran Li, Xin Liu, Yaran Chen","submitted_at":"2024-12-14T10:12:22Z","abstract_excerpt":"Current advanced policy learning methodologies have demonstrated the ability to develop expert-level strategies when provided enough information. However, their requirements, including task-specific rewards, action-labeled expert trajectories, and huge environmental interactions, can be expensive or even unavailable in many scenarios. In contrast, humans can efficiently acquire skills within a few trials and errors by imitating easily accessible internet videos, in the absence of any other supervision. In this paper, we try to let machines replicate this efficient watching-and-learning process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10778","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/2412.10778/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":"2412.10778","created_at":"2026-07-05T10:45:58.369719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10778v2","created_at":"2026-07-05T10:45:58.369719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10778","created_at":"2026-07-05T10:45:58.369719+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKCUZQYZVBEB","created_at":"2026-07-05T10:45:58.369719+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKCUZQYZVBEBWJY4","created_at":"2026-07-05T10:45:58.369719+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKCUZQYZ","created_at":"2026-07-05T10:45:58.369719+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/AKCUZQYZVBEBWJY467VYTFOWBP","json":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP.json","graph_json":"https://pith.science/api/pith-number/AKCUZQYZVBEBWJY467VYTFOWBP/graph.json","events_json":"https://pith.science/api/pith-number/AKCUZQYZVBEBWJY467VYTFOWBP/events.json","paper":"https://pith.science/paper/AKCUZQYZ"},"agent_actions":{"view_html":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP","download_json":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP.json","view_paper":"https://pith.science/paper/AKCUZQYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10778&json=true","fetch_graph":"https://pith.science/api/pith-number/AKCUZQYZVBEBWJY467VYTFOWBP/graph.json","fetch_events":"https://pith.science/api/pith-number/AKCUZQYZVBEBWJY467VYTFOWBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP/action/storage_attestation","attest_author":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP/action/author_attestation","sign_citation":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP/action/citation_signature","submit_replication":"https://pith.science/pith/AKCUZQYZVBEBWJY467VYTFOWBP/action/replication_record"}},"created_at":"2026-07-05T10:45:58.369719+00:00","updated_at":"2026-07-05T10:45:58.369719+00:00"}