{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SHWFFURYJI5DCEXHHNORC7HFGA","short_pith_number":"pith:SHWFFURY","canonical_record":{"source":{"id":"2110.02719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:08:36Z","cross_cats_sorted":[],"title_canon_sha256":"0877e19dd741a8ccf6ef1ef2769ab657c0c64873a1367118d690ee30d726c882","abstract_canon_sha256":"8db926391630c785444a3306027024e79095efca78bf572055e52c15d48d8be7"},"schema_version":"1.0"},"canonical_sha256":"91ec52d2384a3a3112e73b5d117ce53028151ef106c62ffeff4c20d4fa943d47","source":{"kind":"arxiv","id":"2110.02719","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02719","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02719v1","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02719","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"SHWFFURYJI5D","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"SHWFFURYJI5DCEXH","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"SHWFFURY","created_at":"2026-07-05T03:20:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SHWFFURYJI5DCEXHHNORC7HFGA","target":"record","payload":{"canonical_record":{"source":{"id":"2110.02719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:08:36Z","cross_cats_sorted":[],"title_canon_sha256":"0877e19dd741a8ccf6ef1ef2769ab657c0c64873a1367118d690ee30d726c882","abstract_canon_sha256":"8db926391630c785444a3306027024e79095efca78bf572055e52c15d48d8be7"},"schema_version":"1.0"},"canonical_sha256":"91ec52d2384a3a3112e73b5d117ce53028151ef106c62ffeff4c20d4fa943d47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:29.382605Z","signature_b64":"WP9MTDI2dsz6uiIsEzVwvt95vWyFM4k4JHrNIVa57zyzZ/BEjU415DdgMTBqRZJy90dEhbr/c3DKCClZq+m6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91ec52d2384a3a3112e73b5d117ce53028151ef106c62ffeff4c20d4fa943d47","last_reissued_at":"2026-07-05T03:20:29.382254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:29.382254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.02719","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":"2026-07-05T03:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ayUCNK9AnQJ74sS7JmQVPcbuFuRR8ECA/1VIWEEKGIJe0BijDHDjO5zqlNSRJI0h/lCopKq7iXVzFCn+9PlyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:59:02.129662Z"},"content_sha256":"8cc7168f4e234d8d46f7943db0804f03a6001e79d6a24467e3e38defaac795fd","schema_version":"1.0","event_id":"sha256:8cc7168f4e234d8d46f7943db0804f03a6001e79d6a24467e3e38defaac795fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SHWFFURYJI5DCEXHHNORC7HFGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Information Geometry of Unsupervised Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2021-10-06T13:08:36Z","abstract_excerpt":"How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward function. Such algorithms bear a close resemblance to representation learning algorithms (e.g., contrastive learning) in supervised learning, in that both are pretraining algorithms that maximize some approximation to a mutual information objective. While prior work has shown that the set of skills learned by such methods can accelerate downstream RL tasks,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02719","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/2110.02719/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":"2026-07-05T03:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lx3X/+8ZIxjSyI66GBoQ13alN31/DFtaRExlP0kyUxUFCGyd+M5Ld7HSGxqjkQXVq341e4JBPTHrVhgZeVUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:59:02.130176Z"},"content_sha256":"0e73005ad71fc671d33d92e5fd51548c703bd7c013ff44e188052b9853a53808","schema_version":"1.0","event_id":"sha256:0e73005ad71fc671d33d92e5fd51548c703bd7c013ff44e188052b9853a53808"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHWFFURYJI5DCEXHHNORC7HFGA/bundle.json","state_url":"https://pith.science/pith/SHWFFURYJI5DCEXHHNORC7HFGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHWFFURYJI5DCEXHHNORC7HFGA/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":"2026-08-20T09:59:02Z","links":{"resolver":"https://pith.science/pith/SHWFFURYJI5DCEXHHNORC7HFGA","bundle":"https://pith.science/pith/SHWFFURYJI5DCEXHHNORC7HFGA/bundle.json","state":"https://pith.science/pith/SHWFFURYJI5DCEXHHNORC7HFGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHWFFURYJI5DCEXHHNORC7HFGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SHWFFURYJI5DCEXHHNORC7HFGA","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":"8db926391630c785444a3306027024e79095efca78bf572055e52c15d48d8be7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:08:36Z","title_canon_sha256":"0877e19dd741a8ccf6ef1ef2769ab657c0c64873a1367118d690ee30d726c882"},"schema_version":"1.0","source":{"id":"2110.02719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02719","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02719v1","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02719","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"SHWFFURYJI5D","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"SHWFFURYJI5DCEXH","created_at":"2026-07-05T03:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"SHWFFURY","created_at":"2026-07-05T03:20:29Z"}],"graph_snapshots":[{"event_id":"sha256:0e73005ad71fc671d33d92e5fd51548c703bd7c013ff44e188052b9853a53808","target":"graph","created_at":"2026-07-05T03:20:29Z","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/2110.02719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward function. Such algorithms bear a close resemblance to representation learning algorithms (e.g., contrastive learning) in supervised learning, in that both are pretraining algorithms that maximize some approximation to a mutual information objective. While prior work has shown that the set of skills learned by such methods can accelerate downstream RL tasks,","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:08:36Z","title":"The Information Geometry of Unsupervised Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02719","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":"sha256:8cc7168f4e234d8d46f7943db0804f03a6001e79d6a24467e3e38defaac795fd","target":"record","created_at":"2026-07-05T03:20:29Z","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":"8db926391630c785444a3306027024e79095efca78bf572055e52c15d48d8be7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:08:36Z","title_canon_sha256":"0877e19dd741a8ccf6ef1ef2769ab657c0c64873a1367118d690ee30d726c882"},"schema_version":"1.0","source":{"id":"2110.02719","kind":"arxiv","version":1}},"canonical_sha256":"91ec52d2384a3a3112e73b5d117ce53028151ef106c62ffeff4c20d4fa943d47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91ec52d2384a3a3112e73b5d117ce53028151ef106c62ffeff4c20d4fa943d47","first_computed_at":"2026-07-05T03:20:29.382254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:29.382254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WP9MTDI2dsz6uiIsEzVwvt95vWyFM4k4JHrNIVa57zyzZ/BEjU415DdgMTBqRZJy90dEhbr/c3DKCClZq+m6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:29.382605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cc7168f4e234d8d46f7943db0804f03a6001e79d6a24467e3e38defaac795fd","sha256:0e73005ad71fc671d33d92e5fd51548c703bd7c013ff44e188052b9853a53808"],"state_sha256":"39e1f9164d6c002e3cc1604e03faf1777b3a3136b5a0c3ed656da77be04b52ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzZ4Gf6SI5LXH4h2uwfOb+IHwyJBuKg09XeWu5tKcKbzCrmFsglAg8oFOG8uryOdYsOlkFdpZfx2LMxtfA3zAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T09:59:02.134689Z","bundle_sha256":"d4f134a165bc220e50ef73f6b97e4af5108be3d08ec44793d57064606adc7fc2"}}