{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T37QEIBFNSPL3HAIVSKOTEEUV4","short_pith_number":"pith:T37QEIBF","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"},"canonical_sha256":"9eff0220256c9ebd9c08ac94e99094af17c53c84e94d19916face49cf9907bf0","source":{"kind":"arxiv","id":"2606.21271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21271","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21271v1","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21271","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"T37QEIBFNSPL","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"T37QEIBFNSPL3HAI","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"T37QEIBF","created_at":"2026-06-23T01:12:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T37QEIBFNSPL3HAIVSKOTEEUV4","target":"record","payload":{"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"},"canonical_sha256":"9eff0220256c9ebd9c08ac94e99094af17c53c84e94d19916face49cf9907bf0","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"},"source_kind":"arxiv","source_id":"2606.21271","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UxFiWeAz1e2vFhqBbrC06dzYw+JGrTHO/8+E/DzHczajpXrx0zt+xjTzEYVNnUzvIZVKtJ4OitOEQ8pQYcKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T12:21:21.640013Z"},"content_sha256":"7de96061129ac18588bc71278379c43049acbee1ed8b62c4f7980254a7697bbf","schema_version":"1.0","event_id":"sha256:7de96061129ac18588bc71278379c43049acbee1ed8b62c4f7980254a7697bbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T37QEIBFNSPL3HAIVSKOTEEUV4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lmGqxbmzBBDPVNtlPui5OcjWM2+/8gpC9L7/7IYUYHYVWcLRTO6TZNdhbclhF4/OBWc4smbBFKiNgdIbKE7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T12:21:21.640408Z"},"content_sha256":"c7c24c5d5e0b506b80a4ea41b4a0d0928ea468553324a35981f1e0a271b04d7c","schema_version":"1.0","event_id":"sha256:c7c24c5d5e0b506b80a4ea41b4a0d0928ea468553324a35981f1e0a271b04d7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/bundle.json","state_url":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T12:21:21Z","links":{"resolver":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4","bundle":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/bundle.json","state":"https://pith.science/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T37QEIBFNSPL3HAIVSKOTEEUV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T37QEIBFNSPL3HAIVSKOTEEUV4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1ef947fdcf8893d13300e45572f9f8cbe2eee3b9843ca78bed1019f67cc87534","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T09:47:38Z","title_canon_sha256":"2b4c53b2aca703f04bb2b972088c39ad998bb6232bc809480507460af009861c"},"schema_version":"1.0","source":{"id":"2606.21271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21271","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21271v1","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21271","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"T37QEIBFNSPL","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"T37QEIBFNSPL3HAI","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"T37QEIBF","created_at":"2026-06-23T01:12:35Z"}],"graph_snapshots":[{"event_id":"sha256:c7c24c5d5e0b506b80a4ea41b4a0d0928ea468553324a35981f1e0a271b04d7c","target":"graph","created_at":"2026-06-23T01:12:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.21271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Carlo Ciliberto, Marco Prattic\\`o, Massimiliano Pontil, Pietro Novelli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T09:47:38Z","title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21271","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7de96061129ac18588bc71278379c43049acbee1ed8b62c4f7980254a7697bbf","target":"record","created_at":"2026-06-23T01:12:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1ef947fdcf8893d13300e45572f9f8cbe2eee3b9843ca78bed1019f67cc87534","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T09:47:38Z","title_canon_sha256":"2b4c53b2aca703f04bb2b972088c39ad998bb6232bc809480507460af009861c"},"schema_version":"1.0","source":{"id":"2606.21271","kind":"arxiv","version":1}},"canonical_sha256":"9eff0220256c9ebd9c08ac94e99094af17c53c84e94d19916face49cf9907bf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9eff0220256c9ebd9c08ac94e99094af17c53c84e94d19916face49cf9907bf0","first_computed_at":"2026-06-23T01:12:35.532369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:35.532369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lrnSs2aDF3edXkG6gOCnEkS3nQiKfVNMNCKhDShbc5WeY5T8Wy5kR4q82peksQR8wUb7nbP3euNM6c5ZKEAmAw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:35.532840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7de96061129ac18588bc71278379c43049acbee1ed8b62c4f7980254a7697bbf","sha256:c7c24c5d5e0b506b80a4ea41b4a0d0928ea468553324a35981f1e0a271b04d7c"],"state_sha256":"7f09e9e91c742a54a79c466d692a2749a8088f8be427e5ada6551b647c8061ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ELTlMuTjBm7rkP7OU+GuSrG+niBkvatjB9QhjQRxkdItYc811IjH0eo6z2LIOKX9wYU5DmUDfudUfByfdMwnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T12:21:21.642438Z","bundle_sha256":"3e746dc596fa1af11952abf69800f039ff51610eb89be27cd43104581a492f1a"}}