{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MQPN25ODKEMVVXWP6UHI5GSH3T","short_pith_number":"pith:MQPN25OD","canonical_record":{"source":{"id":"2006.09641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T03:58:25Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"0b41aa91c854d90ee3d83d237dfeda6a4291e230e55771b84b6d45613a311b3a","abstract_canon_sha256":"4e55d80914c241fe968cb0468c5d78de948a68202df084fd6d09efbfb5afcafb"},"schema_version":"1.0"},"canonical_sha256":"641edd75c351195adecff50e8e9a47dcffee3b202d1e7d262ee2a78a0c5ce3a1","source":{"kind":"arxiv","id":"2006.09641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09641","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09641v1","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09641","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"MQPN25ODKEMV","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"MQPN25ODKEMVVXWP","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"MQPN25OD","created_at":"2026-07-05T01:11:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MQPN25ODKEMVVXWP6UHI5GSH3T","target":"record","payload":{"canonical_record":{"source":{"id":"2006.09641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T03:58:25Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"0b41aa91c854d90ee3d83d237dfeda6a4291e230e55771b84b6d45613a311b3a","abstract_canon_sha256":"4e55d80914c241fe968cb0468c5d78de948a68202df084fd6d09efbfb5afcafb"},"schema_version":"1.0"},"canonical_sha256":"641edd75c351195adecff50e8e9a47dcffee3b202d1e7d262ee2a78a0c5ce3a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:03.819880Z","signature_b64":"CriBEaC7DnMuehRuM1JCLA+/rZ9AJt5j9jaiwGQlpYTQBBmTeLU2UvaUE299k2976lwhFjYNi1dWgXUtkVyNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641edd75c351195adecff50e8e9a47dcffee3b202d1e7d262ee2a78a0c5ce3a1","last_reissued_at":"2026-07-05T01:11:03.819509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:03.819509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.09641","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":"2026-07-05T01:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fu6NibNwlUFPcADA8BcUPAb/oZyswWJJeU6lfhtE6T+Nvgjbelwd2VQUo4rjo0F57ASg7EEIRKhn+1eeQzQRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:27:42.419054Z"},"content_sha256":"ee206fda39e123bbdadfca822a958b504814da922e209fee3e76fdf6db0302bf","schema_version":"1.0","event_id":"sha256:ee206fda39e123bbdadfca822a958b504814da922e209fee3e76fdf6db0302bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MQPN25ODKEMVVXWP6UHI5GSH3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Curriculum Learning through Value Disagreement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lerrel Pinto, Pieter Abbeel, Yunzhi Zhang","submitted_at":"2020-06-17T03:58:25Z","abstract_excerpt":"Continually solving new, unsolved tasks is the key to learning diverse behaviors. Through reinforcement learning (RL), we have made massive strides towards solving tasks that have a single goal. However, in the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. When biological agents learn, there is often an organized and meaningful order to which learning happens. Inspired by this, we propose setting up an automatic curriculum for goals that the agent needs to solve. Our key insight is that if we can sample goals"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09641","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/2006.09641/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":"2026-07-05T01:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"toqpiu/NV3q3gpVE6dSGF9N10KleDMulKuPz/D+TKg4cLif0aMtSbsbedcSeyCqldHPavbTGaoscE2af6mfLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:27:42.419432Z"},"content_sha256":"8e5475424d4e2fbb699d005380508106de785cf9f622bacd733d61fe4a176767","schema_version":"1.0","event_id":"sha256:8e5475424d4e2fbb699d005380508106de785cf9f622bacd733d61fe4a176767"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQPN25ODKEMVVXWP6UHI5GSH3T/bundle.json","state_url":"https://pith.science/pith/MQPN25ODKEMVVXWP6UHI5GSH3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQPN25ODKEMVVXWP6UHI5GSH3T/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":"2026-08-18T18:27:42Z","links":{"resolver":"https://pith.science/pith/MQPN25ODKEMVVXWP6UHI5GSH3T","bundle":"https://pith.science/pith/MQPN25ODKEMVVXWP6UHI5GSH3T/bundle.json","state":"https://pith.science/pith/MQPN25ODKEMVVXWP6UHI5GSH3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQPN25ODKEMVVXWP6UHI5GSH3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MQPN25ODKEMVVXWP6UHI5GSH3T","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":"4e55d80914c241fe968cb0468c5d78de948a68202df084fd6d09efbfb5afcafb","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T03:58:25Z","title_canon_sha256":"0b41aa91c854d90ee3d83d237dfeda6a4291e230e55771b84b6d45613a311b3a"},"schema_version":"1.0","source":{"id":"2006.09641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.09641","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.09641v1","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09641","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"MQPN25ODKEMV","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"MQPN25ODKEMVVXWP","created_at":"2026-07-05T01:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"MQPN25OD","created_at":"2026-07-05T01:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:8e5475424d4e2fbb699d005380508106de785cf9f622bacd733d61fe4a176767","target":"graph","created_at":"2026-07-05T01:11:03Z","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/2006.09641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continually solving new, unsolved tasks is the key to learning diverse behaviors. Through reinforcement learning (RL), we have made massive strides towards solving tasks that have a single goal. However, in the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. When biological agents learn, there is often an organized and meaningful order to which learning happens. Inspired by this, we propose setting up an automatic curriculum for goals that the agent needs to solve. Our key insight is that if we can sample goals","authors_text":"Lerrel Pinto, Pieter Abbeel, Yunzhi Zhang","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T03:58:25Z","title":"Automatic Curriculum Learning through Value Disagreement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09641","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:ee206fda39e123bbdadfca822a958b504814da922e209fee3e76fdf6db0302bf","target":"record","created_at":"2026-07-05T01:11:03Z","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":"4e55d80914c241fe968cb0468c5d78de948a68202df084fd6d09efbfb5afcafb","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T03:58:25Z","title_canon_sha256":"0b41aa91c854d90ee3d83d237dfeda6a4291e230e55771b84b6d45613a311b3a"},"schema_version":"1.0","source":{"id":"2006.09641","kind":"arxiv","version":1}},"canonical_sha256":"641edd75c351195adecff50e8e9a47dcffee3b202d1e7d262ee2a78a0c5ce3a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"641edd75c351195adecff50e8e9a47dcffee3b202d1e7d262ee2a78a0c5ce3a1","first_computed_at":"2026-07-05T01:11:03.819509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:03.819509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CriBEaC7DnMuehRuM1JCLA+/rZ9AJt5j9jaiwGQlpYTQBBmTeLU2UvaUE299k2976lwhFjYNi1dWgXUtkVyNAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:03.819880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.09641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee206fda39e123bbdadfca822a958b504814da922e209fee3e76fdf6db0302bf","sha256:8e5475424d4e2fbb699d005380508106de785cf9f622bacd733d61fe4a176767"],"state_sha256":"52923d7712d7a2ae43a13a3d2826323817200a7b548a31999efe54b2be361a02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/cpHQUyzc6DhgR5T1s+LsGtwjZs0ZxMGanbJ1aoCJpctjhOwFQaqPClNqPmvjpy0r9AwYtprWl7tVuISSnw8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:27:42.423296Z","bundle_sha256":"3f239aabeaec990077c36dd3b9b94022eb73d3187020b61ad1aa42eb78016754"}}