{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FHADIYOB4LPIBYWZHQIGLYDD5Z","short_pith_number":"pith:FHADIYOB","canonical_record":{"source":{"id":"2311.11385","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-19T18:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"b9e90df2cf42fe7965768a60ef48d1c1bad55fb59873b42723401f9c8f0bbdc8","abstract_canon_sha256":"eac0f61dbd5192382e0bee098f0c628bada0b628b1e1af30fda69c786eb2fb1e"},"schema_version":"1.0"},"canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","source":{"kind":"arxiv","id":"2311.11385","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11385","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11385v2","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11385","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"FHADIYOB4LPI","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"FHADIYOB4LPIBYWZ","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"FHADIYOB","created_at":"2026-07-05T08:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FHADIYOB4LPIBYWZHQIGLYDD5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2311.11385","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-19T18:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"b9e90df2cf42fe7965768a60ef48d1c1bad55fb59873b42723401f9c8f0bbdc8","abstract_canon_sha256":"eac0f61dbd5192382e0bee098f0c628bada0b628b1e1af30fda69c786eb2fb1e"},"schema_version":"1.0"},"canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:42.020144Z","signature_b64":"ZlvqVrq3KV6Y34EB/xCaK/1loX6HJE0SP+6gR6EVE9MWxzf5trhuv5mrij4+/NrRD77vnXuUp8CakcjaxwxECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","last_reissued_at":"2026-07-05T08:15:42.019611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:42.019611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.11385","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":"2026-07-05T08:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ps8Rg6ZYOq4QvAsO+G4Fy2JxzrW+0kxQ35VPVXMpA4yIP44c25YDZo8uZkZoP84TogD4cqiDYnzYApwcfMFEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:46:37.204426Z"},"content_sha256":"030e594a1e98219b0086f397c711a802bd8f820829617b4aa6f455cf6dc7be38","schema_version":"1.0","event_id":"sha256:030e594a1e98219b0086f397c711a802bd8f820829617b4aa6f455cf6dc7be38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FHADIYOB4LPIBYWZHQIGLYDD5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Jan Peters","submitted_at":"2023-11-19T18:09:25Z","abstract_excerpt":"Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique and common characteristics of the tasks. Tasks may exhibit similarities in terms of skills, objects, or physical properties while leveraging their representations eases the achievement of a universal policy. Nevertheless, the pursuit of learning a shared set of diverse representations is still an open challenge. In this paper, we introduce a novel approach fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11385","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/2311.11385/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":"2026-07-05T08:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHlm+cEQapmKRvo7TNyh/BL1Sjd0SjDlCqWhFUUYu42uUErXeJSFbvf+mZMAT/JkvalxmzniniQjjsi4XdMbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:46:37.204997Z"},"content_sha256":"4a70b8fd7a924008fdd5a2be3e171c37800a23ccbf5f296728865344e6b1fa3e","schema_version":"1.0","event_id":"sha256:4a70b8fd7a924008fdd5a2be3e171c37800a23ccbf5f296728865344e6b1fa3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/bundle.json","state_url":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/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":"2026-08-07T16:46:37Z","links":{"resolver":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z","bundle":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/bundle.json","state":"https://pith.science/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHADIYOB4LPIBYWZHQIGLYDD5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FHADIYOB4LPIBYWZHQIGLYDD5Z","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":"eac0f61dbd5192382e0bee098f0c628bada0b628b1e1af30fda69c786eb2fb1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-19T18:09:25Z","title_canon_sha256":"b9e90df2cf42fe7965768a60ef48d1c1bad55fb59873b42723401f9c8f0bbdc8"},"schema_version":"1.0","source":{"id":"2311.11385","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11385","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11385v2","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11385","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"FHADIYOB4LPI","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"FHADIYOB4LPIBYWZ","created_at":"2026-07-05T08:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"FHADIYOB","created_at":"2026-07-05T08:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:4a70b8fd7a924008fdd5a2be3e171c37800a23ccbf5f296728865344e6b1fa3e","target":"graph","created_at":"2026-07-05T08:15:42Z","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/2311.11385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique and common characteristics of the tasks. Tasks may exhibit similarities in terms of skills, objects, or physical properties while leveraging their representations eases the achievement of a universal policy. Nevertheless, the pursuit of learning a shared set of diverse representations is still an open challenge. In this paper, we introduce a novel approach fo","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Jan Peters","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-19T18:09:25Z","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11385","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":"sha256:030e594a1e98219b0086f397c711a802bd8f820829617b4aa6f455cf6dc7be38","target":"record","created_at":"2026-07-05T08:15:42Z","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":"eac0f61dbd5192382e0bee098f0c628bada0b628b1e1af30fda69c786eb2fb1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-19T18:09:25Z","title_canon_sha256":"b9e90df2cf42fe7965768a60ef48d1c1bad55fb59873b42723401f9c8f0bbdc8"},"schema_version":"1.0","source":{"id":"2311.11385","kind":"arxiv","version":2}},"canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29c03461c1e2de80e2d93c1065e063ee582732702f37cd6c9b45bc19d649aa88","first_computed_at":"2026-07-05T08:15:42.019611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:42.019611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZlvqVrq3KV6Y34EB/xCaK/1loX6HJE0SP+6gR6EVE9MWxzf5trhuv5mrij4+/NrRD77vnXuUp8CakcjaxwxECw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:42.020144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.11385","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:030e594a1e98219b0086f397c711a802bd8f820829617b4aa6f455cf6dc7be38","sha256:4a70b8fd7a924008fdd5a2be3e171c37800a23ccbf5f296728865344e6b1fa3e"],"state_sha256":"f65680c674cf1ebb18ddb30c5f33ede76e3db59bb1667b0bd8aaa13858a4f28d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3BCgD9EEpJNNSGUru9Aek0IHtSCmWjLnnrh/BT9wdd/WhZ6m3BHEOMFmyR0+O8lVn78o6NQrhDeO/cEqz/DtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:46:37.210456Z","bundle_sha256":"43810517948900dd8bcca8644617d0ed25e89093a7aa1288180b8a84246f1b7a"}}