{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LSWZUXBGPSYQRY3F3GLYTUQGY6","short_pith_number":"pith:LSWZUXBG","canonical_record":{"source":{"id":"1901.09720","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:00:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"16cc9f8f7ff2e08585f70701e7fccb7c129f7eca1013cc75a36b12fd67436009","abstract_canon_sha256":"26fe7be8a7268c563ea8b9425b440f414c0fac68a1639c82870fcb1d0bb92a1b"},"schema_version":"1.0"},"canonical_sha256":"5cad9a5c267cb108e365d99789d206c79db72814eb728ade019927b799af27a4","source":{"kind":"arxiv","id":"1901.09720","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09720","created_at":"2026-05-17T23:50:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09720v4","created_at":"2026-05-17T23:50:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09720","created_at":"2026-05-17T23:50:33Z"},{"alias_kind":"pith_short_12","alias_value":"LSWZUXBGPSYQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LSWZUXBGPSYQRY3F","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LSWZUXBG","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LSWZUXBGPSYQRY3F3GLYTUQGY6","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09720","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:00:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"16cc9f8f7ff2e08585f70701e7fccb7c129f7eca1013cc75a36b12fd67436009","abstract_canon_sha256":"26fe7be8a7268c563ea8b9425b440f414c0fac68a1639c82870fcb1d0bb92a1b"},"schema_version":"1.0"},"canonical_sha256":"5cad9a5c267cb108e365d99789d206c79db72814eb728ade019927b799af27a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:33.353849Z","signature_b64":"+ZPAW1PJgxorOujbuwwRUPkom/BOrKvVMjKLOKDkOxE8qxN84x6yJL67Y60qXrPzPBdEw14vGPzWhKhLDlkODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cad9a5c267cb108e365d99789d206c79db72814eb728ade019927b799af27a4","last_reissued_at":"2026-05-17T23:50:33.353191Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:33.353191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09720","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9Y7J4el653FOhIXFlYNobsnIkseASyihcxY0KisowUznUmd5afNAmGDx8bH0vXq+FEvv+b/EuIFo03RLFWtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:05:00.075036Z"},"content_sha256":"d4ee72c3f553332ce9f213a35d5f999897486565622f9379adf8819c053bfdb2","schema_version":"1.0","event_id":"sha256:d4ee72c3f553332ce9f213a35d5f999897486565622f9379adf8819c053bfdb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LSWZUXBGPSYQRY3F3GLYTUQGY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Colas, Mohamed Chetouani, Olivier Sigaud, Pierre Fournier","submitted_at":"2019-01-28T15:00:29Z","abstract_excerpt":"In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions. We argue that this setting defines a realistic scenario and we present a generic discrete-state discrete-action model of such environments. To learn in this environment, we propose an unsupervised reinforcement learning agent called CLIC for Curriculum Learning and Imitation for Control. CLIC learns to control individual objects in its environment, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09720","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:50:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FG+BlI0xXT6IBdut//swkwoqQ61bs1dy50VhbIvUAqt3KgKz8amyHJQOUCJaPwI4hWm3OAeIUZSmAsJlO2GTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:05:00.075761Z"},"content_sha256":"ddfe11660cd355d2d69933e698dcfadd689e0c29952853b5fc9959363712e773","schema_version":"1.0","event_id":"sha256:ddfe11660cd355d2d69933e698dcfadd689e0c29952853b5fc9959363712e773"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6/bundle.json","state_url":"https://pith.science/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6/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":"2026-05-25T16:05:00Z","links":{"resolver":"https://pith.science/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6","bundle":"https://pith.science/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6/bundle.json","state":"https://pith.science/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSWZUXBGPSYQRY3F3GLYTUQGY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LSWZUXBGPSYQRY3F3GLYTUQGY6","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":"26fe7be8a7268c563ea8b9425b440f414c0fac68a1639c82870fcb1d0bb92a1b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:00:29Z","title_canon_sha256":"16cc9f8f7ff2e08585f70701e7fccb7c129f7eca1013cc75a36b12fd67436009"},"schema_version":"1.0","source":{"id":"1901.09720","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09720","created_at":"2026-05-17T23:50:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09720v4","created_at":"2026-05-17T23:50:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09720","created_at":"2026-05-17T23:50:33Z"},{"alias_kind":"pith_short_12","alias_value":"LSWZUXBGPSYQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LSWZUXBGPSYQRY3F","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LSWZUXBG","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:ddfe11660cd355d2d69933e698dcfadd689e0c29952853b5fc9959363712e773","target":"graph","created_at":"2026-05-17T23:50:33Z","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"},"paper":{"abstract_excerpt":"In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions. We argue that this setting defines a realistic scenario and we present a generic discrete-state discrete-action model of such environments. To learn in this environment, we propose an unsupervised reinforcement learning agent called CLIC for Curriculum Learning and Imitation for Control. CLIC learns to control individual objects in its environment, ","authors_text":"C\\'edric Colas, Mohamed Chetouani, Olivier Sigaud, Pierre Fournier","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:00:29Z","title":"CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09720","kind":"arxiv","version":4},"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:d4ee72c3f553332ce9f213a35d5f999897486565622f9379adf8819c053bfdb2","target":"record","created_at":"2026-05-17T23:50:33Z","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":"26fe7be8a7268c563ea8b9425b440f414c0fac68a1639c82870fcb1d0bb92a1b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:00:29Z","title_canon_sha256":"16cc9f8f7ff2e08585f70701e7fccb7c129f7eca1013cc75a36b12fd67436009"},"schema_version":"1.0","source":{"id":"1901.09720","kind":"arxiv","version":4}},"canonical_sha256":"5cad9a5c267cb108e365d99789d206c79db72814eb728ade019927b799af27a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cad9a5c267cb108e365d99789d206c79db72814eb728ade019927b799af27a4","first_computed_at":"2026-05-17T23:50:33.353191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:33.353191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ZPAW1PJgxorOujbuwwRUPkom/BOrKvVMjKLOKDkOxE8qxN84x6yJL67Y60qXrPzPBdEw14vGPzWhKhLDlkODA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:33.353849Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09720","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4ee72c3f553332ce9f213a35d5f999897486565622f9379adf8819c053bfdb2","sha256:ddfe11660cd355d2d69933e698dcfadd689e0c29952853b5fc9959363712e773"],"state_sha256":"279b43f46205aa064f6edc11c443971e5090b0f61605a90e0d3adb04d4b8794b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jENzt4Z7KCiiLzl6SqOYH+Wk7rrmwBs3/8P8XNTlPadNbuusJwvi0PlxphhcaFpoacCEvqi7a50AiVun5f+YBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:05:00.079617Z","bundle_sha256":"b63a358f704f2552de02a01b23535b4541a1b2e3b70ba2159304c38ed5c52cb4"}}