{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T37QEIBFNSPL3HAIVSKOTEEUV4","short_pith_number":"pith:T37QEIBF","schema_version":"1.0","canonical_sha256":"9eff0220256c9ebd9c08ac94e99094af17c53c84e94d19916face49cf9907bf0","source":{"kind":"arxiv","id":"2606.21271","version":1},"attestation_state":"computed","paper":{"title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Marco Prattic\\`o, Massimiliano Pontil, Pietro Novelli","submitted_at":"2026-06-19T09:47:38Z","abstract_excerpt":"Sparse rewards pose a central challenge in reinforcement learning, since agents receive no informative signal until they reach their goal. Intrinsic-reward methods address this issue by optimizing non-stationary objectives such as novelty, prediction error, or skill diversity, thereby injecting a supervision signal into the problem. While effective, these methods often require that the extrinsic (sparse) reward can be evaluated -- either online or during offline relabeling of the stored transitions. This limitation is particularly vexing for multi-task, meta-, and continual reinforcement learn"},"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":"2606.21271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T09:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"2b4c53b2aca703f04bb2b972088c39ad998bb6232bc809480507460af009861c","abstract_canon_sha256":"1ef947fdcf8893d13300e45572f9f8cbe2eee3b9843ca78bed1019f67cc87534"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:35.532840Z","signature_b64":"lrnSs2aDF3edXkG6gOCnEkS3nQiKfVNMNCKhDShbc5WeY5T8Wy5kR4q82peksQR8wUb7nbP3euNM6c5ZKEAmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eff0220256c9ebd9c08ac94e99094af17c53c84e94d19916face49cf9907bf0","last_reissued_at":"2026-06-23T01:12:35.532369Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:35.532369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Marco Prattic\\`o, Massimiliano Pontil, Pietro Novelli","submitted_at":"2026-06-19T09:47:38Z","abstract_excerpt":"Sparse rewards pose a central challenge in reinforcement learning, since agents receive no informative signal until they reach their goal. Intrinsic-reward methods address this issue by optimizing non-stationary objectives such as novelty, prediction error, or skill diversity, thereby injecting a supervision signal into the problem. While effective, these methods often require that the extrinsic (sparse) reward can be evaluated -- either online or during offline relabeling of the stored transitions. This limitation is particularly vexing for multi-task, meta-, and continual reinforcement learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21271","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/2606.21271/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":"2606.21271","created_at":"2026-06-23T01:12:35.532446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21271v1","created_at":"2026-06-23T01:12:35.532446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21271","created_at":"2026-06-23T01:12:35.532446+00:00"},{"alias_kind":"pith_short_12","alias_value":"T37QEIBFNSPL","created_at":"2026-06-23T01:12:35.532446+00:00"},{"alias_kind":"pith_short_16","alias_value":"T37QEIBFNSPL3HAI","created_at":"2026-06-23T01:12:35.532446+00:00"},{"alias_kind":"pith_short_8","alias_value":"T37QEIBF","created_at":"2026-06-23T01:12:35.532446+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/T37QEIBFNSPL3HAIVSKOTEEUV4","json":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4.json","graph_json":"https://pith.science/api/pith-number/T37QEIBFNSPL3HAIVSKOTEEUV4/graph.json","events_json":"https://pith.science/api/pith-number/T37QEIBFNSPL3HAIVSKOTEEUV4/events.json","paper":"https://pith.science/paper/T37QEIBF"},"agent_actions":{"view_html":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4","download_json":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4.json","view_paper":"https://pith.science/paper/T37QEIBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21271&json=true","fetch_graph":"https://pith.science/api/pith-number/T37QEIBFNSPL3HAIVSKOTEEUV4/graph.json","fetch_events":"https://pith.science/api/pith-number/T37QEIBFNSPL3HAIVSKOTEEUV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/action/storage_attestation","attest_author":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/action/author_attestation","sign_citation":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/action/citation_signature","submit_replication":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/action/replication_record"}},"created_at":"2026-06-23T01:12:35.532446+00:00","updated_at":"2026-06-23T01:12:35.532446+00:00"}