{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3VUBO462T6LJPRE6YO3AAWZEX2","short_pith_number":"pith:3VUBO462","canonical_record":{"source":{"id":"2004.02860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-06T17:50:28Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"2aad1c8695ef071d7c84747099322e60963e4bbd94d577fc783b69a07a75b06f","abstract_canon_sha256":"8bc5324702522bd948e8a4406cbbb74f3fa170419575f97244965cba4d454a4f"},"schema_version":"1.0"},"canonical_sha256":"dd681773da9f9697c49ec3b6005b24be98eea0de6df9d0cbeeec25c4c3398cc7","source":{"kind":"arxiv","id":"2004.02860","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02860","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02860v2","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02860","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"3VUBO462T6LJ","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"pith_short_16","alias_value":"3VUBO462T6LJPRE6","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"pith_short_8","alias_value":"3VUBO462","created_at":"2026-07-05T01:52:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3VUBO462T6LJPRE6YO3AAWZEX2","target":"record","payload":{"canonical_record":{"source":{"id":"2004.02860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-06T17:50:28Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"2aad1c8695ef071d7c84747099322e60963e4bbd94d577fc783b69a07a75b06f","abstract_canon_sha256":"8bc5324702522bd948e8a4406cbbb74f3fa170419575f97244965cba4d454a4f"},"schema_version":"1.0"},"canonical_sha256":"dd681773da9f9697c49ec3b6005b24be98eea0de6df9d0cbeeec25c4c3398cc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:34.958852Z","signature_b64":"rWuuYZca+7NNKZPNuxgEG04Pk7wEEymBr7ssxRAF7Yrmip2vhONGiLUsChLej98EVkQ5jIV3LB6DVxt/DehNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd681773da9f9697c49ec3b6005b24be98eea0de6df9d0cbeeec25c4c3398cc7","last_reissued_at":"2026-07-05T01:52:34.958309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:34.958309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.02860","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:52:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6qAp0WPoW7RazcL91ANb8UlaaMh7oW0MjF6dpwZB//7MipKHahst5GcTnW3KbyKgGQIcXzsU7Ev0+ZnhAkRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:16:40.402137Z"},"content_sha256":"bbad9b57234e2ad42dde9a615b5197cb8e4883a2817b77a23b50aa0c09325a29","schema_version":"1.0","event_id":"sha256:bbad9b57234e2ad42dde9a615b5197cb8e4883a2817b77a23b50aa0c09325a29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3VUBO462T6LJPRE6YO3AAWZEX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly-Supervised Reinforcement Learning for Controllable Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Chelsea Finn, Lisa Lee, Ruslan Salakhutdinov, Shixiang Shane Gu","submitted_at":"2020-04-06T17:50:28Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical \"chaff\" tasks. We show that this learned subspace enables efficient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02860","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/2004.02860/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":"2026-07-05T01:52:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cU7olkSlNyUXao8bMQa2cs8Kp+0NRUrm7zdJNUf1OXi8sGDQjowCup03DnqfQodYE1sQR5dqHKc/66igN2d6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:16:40.403068Z"},"content_sha256":"e71ada8e87b302c984032d04174199d4b3fc9c5dca614e469cc6121c0fb85db6","schema_version":"1.0","event_id":"sha256:e71ada8e87b302c984032d04174199d4b3fc9c5dca614e469cc6121c0fb85db6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VUBO462T6LJPRE6YO3AAWZEX2/bundle.json","state_url":"https://pith.science/pith/3VUBO462T6LJPRE6YO3AAWZEX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VUBO462T6LJPRE6YO3AAWZEX2/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":"2026-08-04T11:16:40Z","links":{"resolver":"https://pith.science/pith/3VUBO462T6LJPRE6YO3AAWZEX2","bundle":"https://pith.science/pith/3VUBO462T6LJPRE6YO3AAWZEX2/bundle.json","state":"https://pith.science/pith/3VUBO462T6LJPRE6YO3AAWZEX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VUBO462T6LJPRE6YO3AAWZEX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3VUBO462T6LJPRE6YO3AAWZEX2","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":"8bc5324702522bd948e8a4406cbbb74f3fa170419575f97244965cba4d454a4f","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-06T17:50:28Z","title_canon_sha256":"2aad1c8695ef071d7c84747099322e60963e4bbd94d577fc783b69a07a75b06f"},"schema_version":"1.0","source":{"id":"2004.02860","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02860","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02860v2","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02860","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"3VUBO462T6LJ","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"pith_short_16","alias_value":"3VUBO462T6LJPRE6","created_at":"2026-07-05T01:52:34Z"},{"alias_kind":"pith_short_8","alias_value":"3VUBO462","created_at":"2026-07-05T01:52:34Z"}],"graph_snapshots":[{"event_id":"sha256:e71ada8e87b302c984032d04174199d4b3fc9c5dca614e469cc6121c0fb85db6","target":"graph","created_at":"2026-07-05T01:52:34Z","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/2004.02860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical \"chaff\" tasks. We show that this learned subspace enables efficient ","authors_text":"Benjamin Eysenbach, Chelsea Finn, Lisa Lee, Ruslan Salakhutdinov, Shixiang Shane Gu","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-06T17:50:28Z","title":"Weakly-Supervised Reinforcement Learning for Controllable Behavior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02860","kind":"arxiv","version":2},"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:bbad9b57234e2ad42dde9a615b5197cb8e4883a2817b77a23b50aa0c09325a29","target":"record","created_at":"2026-07-05T01:52:34Z","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":"8bc5324702522bd948e8a4406cbbb74f3fa170419575f97244965cba4d454a4f","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-06T17:50:28Z","title_canon_sha256":"2aad1c8695ef071d7c84747099322e60963e4bbd94d577fc783b69a07a75b06f"},"schema_version":"1.0","source":{"id":"2004.02860","kind":"arxiv","version":2}},"canonical_sha256":"dd681773da9f9697c49ec3b6005b24be98eea0de6df9d0cbeeec25c4c3398cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd681773da9f9697c49ec3b6005b24be98eea0de6df9d0cbeeec25c4c3398cc7","first_computed_at":"2026-07-05T01:52:34.958309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:52:34.958309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWuuYZca+7NNKZPNuxgEG04Pk7wEEymBr7ssxRAF7Yrmip2vhONGiLUsChLej98EVkQ5jIV3LB6DVxt/DehNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:52:34.958852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02860","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbad9b57234e2ad42dde9a615b5197cb8e4883a2817b77a23b50aa0c09325a29","sha256:e71ada8e87b302c984032d04174199d4b3fc9c5dca614e469cc6121c0fb85db6"],"state_sha256":"60466e8cc15772ef4e201dde3525960f62b530fd1d097f00aa0b39829579b2f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSMFK0+2IE17HN2m+D9TxzMTdEJnQAGWRmygMLQ5EUpSW1EnNzUk3KwM9YpIoaBjryN5x4C5HF13fDJ+IuoQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:16:40.428163Z","bundle_sha256":"b932bf65956d37721f1ba2baceab9ca42515e64accec786f9c836663460315ab"}}