{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MQPUQ5FBAY7BSYEGHQQJX5VJDP","short_pith_number":"pith:MQPUQ5FB","schema_version":"1.0","canonical_sha256":"641f4874a1063e1960863c209bf6a91bf8ca81a4be36568f0329f423ce88ecbc","source":{"kind":"arxiv","id":"2506.11967","version":1},"attestation_state":"computed","paper":{"title":"Visual Pre-Training on Unlabeled Images using Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dibya Ghosh, Sergey Levine","submitted_at":"2025-06-13T17:25:27Z","abstract_excerpt":"In reinforcement learning (RL), value-based algorithms learn to associate each observation with the states and rewards that are likely to be reached from it. We observe that many self-supervised image pre-training methods bear similarity to this formulation: learning features that associate crops of images with those of nearby views, e.g., by taking a different crop or color augmentation. In this paper, we complete this analogy and explore a method that directly casts pre-training on unlabeled image data like web crawls and video frames as an RL problem. We train a general value function in a "},"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":"2506.11967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T17:25:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"193bb8f7f855b227a42bbf1c6734f8efa2ef7ac7ea6c482872844e73cf48208f","abstract_canon_sha256":"1e1541ddb37592264c313d92fab38754a36818da32fed3efa1b894b9fd416746"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:13.614485Z","signature_b64":"ZJyEa/+4GD1CU3PoOXXsQKFlweQ3rRQtUkFD3ksjZ581QqdlYPXmt9nt1ekJjN56ht9Lz6zVbUWyaYHR87VOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641f4874a1063e1960863c209bf6a91bf8ca81a4be36568f0329f423ce88ecbc","last_reissued_at":"2026-07-05T11:21:13.613998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:13.613998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Pre-Training on Unlabeled Images using Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dibya Ghosh, Sergey Levine","submitted_at":"2025-06-13T17:25:27Z","abstract_excerpt":"In reinforcement learning (RL), value-based algorithms learn to associate each observation with the states and rewards that are likely to be reached from it. We observe that many self-supervised image pre-training methods bear similarity to this formulation: learning features that associate crops of images with those of nearby views, e.g., by taking a different crop or color augmentation. In this paper, we complete this analogy and explore a method that directly casts pre-training on unlabeled image data like web crawls and video frames as an RL problem. We train a general value function in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11967","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/2506.11967/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":"2506.11967","created_at":"2026-07-05T11:21:13.614056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11967v1","created_at":"2026-07-05T11:21:13.614056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11967","created_at":"2026-07-05T11:21:13.614056+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQPUQ5FBAY7B","created_at":"2026-07-05T11:21:13.614056+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQPUQ5FBAY7BSYEG","created_at":"2026-07-05T11:21:13.614056+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQPUQ5FB","created_at":"2026-07-05T11:21:13.614056+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/MQPUQ5FBAY7BSYEGHQQJX5VJDP","json":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP.json","graph_json":"https://pith.science/api/pith-number/MQPUQ5FBAY7BSYEGHQQJX5VJDP/graph.json","events_json":"https://pith.science/api/pith-number/MQPUQ5FBAY7BSYEGHQQJX5VJDP/events.json","paper":"https://pith.science/paper/MQPUQ5FB"},"agent_actions":{"view_html":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP","download_json":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP.json","view_paper":"https://pith.science/paper/MQPUQ5FB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11967&json=true","fetch_graph":"https://pith.science/api/pith-number/MQPUQ5FBAY7BSYEGHQQJX5VJDP/graph.json","fetch_events":"https://pith.science/api/pith-number/MQPUQ5FBAY7BSYEGHQQJX5VJDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP/action/storage_attestation","attest_author":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP/action/author_attestation","sign_citation":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP/action/citation_signature","submit_replication":"https://pith.science/pith/MQPUQ5FBAY7BSYEGHQQJX5VJDP/action/replication_record"}},"created_at":"2026-07-05T11:21:13.614056+00:00","updated_at":"2026-07-05T11:21:13.614056+00:00"}