{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4NCRIN77CR4P35OXLZEVQU6HTU","short_pith_number":"pith:4NCRIN77","canonical_record":{"source":{"id":"2006.16908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T15:38:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"242ba8f6ed52bf6036db108ed808663fcfd3d07db237acc77dda57671f0eb2f0","abstract_canon_sha256":"f0c981aab0e1135a2e1c95ece7ca49b447195b825b6b8153f3a1679263b52325"},"schema_version":"1.0"},"canonical_sha256":"e3451437ff1478fdf5d75e495853c79d0b3888d4aaeb804122f39c8c4cb10388","source":{"kind":"arxiv","id":"2006.16908","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16908","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16908v2","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16908","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"4NCRIN77CR4P","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"4NCRIN77CR4P35OX","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"4NCRIN77","created_at":"2026-07-05T02:08:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4NCRIN77CR4P35OXLZEVQU6HTU","target":"record","payload":{"canonical_record":{"source":{"id":"2006.16908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T15:38:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"242ba8f6ed52bf6036db108ed808663fcfd3d07db237acc77dda57671f0eb2f0","abstract_canon_sha256":"f0c981aab0e1135a2e1c95ece7ca49b447195b825b6b8153f3a1679263b52325"},"schema_version":"1.0"},"canonical_sha256":"e3451437ff1478fdf5d75e495853c79d0b3888d4aaeb804122f39c8c4cb10388","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:18.250229Z","signature_b64":"C12pkpgMNalRkWdoDyp4MhNGs9efDy6dbXl2x6LlFE23bx9Mgpw/am7Cdo240ixavZKdxdoQN7kbKbsPqIVSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3451437ff1478fdf5d75e495853c79d0b3888d4aaeb804122f39c8c4cb10388","last_reissued_at":"2026-07-05T02:08:18.249744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:18.249744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.16908","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":"2026-07-05T02:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R1+9ckSNsJ6jRNma6DeoLt6sSJ4+Hdmvl/jPQkBmQnGIKkcp+ogGJoMjpi8p2fX6BW5vXB/C09hyb6oGjESyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:11:58.292927Z"},"content_sha256":"60378847d77664b80d05bc8f0f3b3d2b94b729d391663393bc0cd384af27b47b","schema_version":"1.0","event_id":"sha256:60378847d77664b80d05bc8f0f3b3d2b94b729d391663393bc0cd384af27b47b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4NCRIN77CR4P35OXLZEVQU6HTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel E. Worrall, Elise van der Pol, Frans A. Oliehoek, Herke van Hoof, Max Welling","submitted_at":"2020-06-30T15:38:37Z","abstract_excerpt":"This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep reinforcement learning do not usually exploit knowledge about such structure. By building this prior knowledge into policy and value networks using an equivariance constraint, we can reduce the size of the solution space. We specifically focus on group-structured symmetries (invertible transformations). Additionally, we introduce an easy method for constructing equ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16908","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/2006.16908/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":"2026-07-05T02:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+wAnkUPD+BWGdjLpTy98OPD9c703vHgkZDWjhvL/8S/vIDYg2szvfJDCiSg2cgHIUbQDlBb/RSscQ6zGCALAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:11:58.293899Z"},"content_sha256":"9954a874fa0fdaa12b133ee94183528073d4ebfc628ecc0bad1519b5bc538319","schema_version":"1.0","event_id":"sha256:9954a874fa0fdaa12b133ee94183528073d4ebfc628ecc0bad1519b5bc538319"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NCRIN77CR4P35OXLZEVQU6HTU/bundle.json","state_url":"https://pith.science/pith/4NCRIN77CR4P35OXLZEVQU6HTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NCRIN77CR4P35OXLZEVQU6HTU/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":"2026-08-11T01:11:58Z","links":{"resolver":"https://pith.science/pith/4NCRIN77CR4P35OXLZEVQU6HTU","bundle":"https://pith.science/pith/4NCRIN77CR4P35OXLZEVQU6HTU/bundle.json","state":"https://pith.science/pith/4NCRIN77CR4P35OXLZEVQU6HTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NCRIN77CR4P35OXLZEVQU6HTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4NCRIN77CR4P35OXLZEVQU6HTU","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":"f0c981aab0e1135a2e1c95ece7ca49b447195b825b6b8153f3a1679263b52325","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T15:38:37Z","title_canon_sha256":"242ba8f6ed52bf6036db108ed808663fcfd3d07db237acc77dda57671f0eb2f0"},"schema_version":"1.0","source":{"id":"2006.16908","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16908","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16908v2","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16908","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"4NCRIN77CR4P","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"4NCRIN77CR4P35OX","created_at":"2026-07-05T02:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"4NCRIN77","created_at":"2026-07-05T02:08:18Z"}],"graph_snapshots":[{"event_id":"sha256:9954a874fa0fdaa12b133ee94183528073d4ebfc628ecc0bad1519b5bc538319","target":"graph","created_at":"2026-07-05T02:08:18Z","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/2006.16908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep reinforcement learning do not usually exploit knowledge about such structure. By building this prior knowledge into policy and value networks using an equivariance constraint, we can reduce the size of the solution space. We specifically focus on group-structured symmetries (invertible transformations). Additionally, we introduce an easy method for constructing equ","authors_text":"Daniel E. Worrall, Elise van der Pol, Frans A. Oliehoek, Herke van Hoof, Max Welling","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T15:38:37Z","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16908","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":"sha256:60378847d77664b80d05bc8f0f3b3d2b94b729d391663393bc0cd384af27b47b","target":"record","created_at":"2026-07-05T02:08:18Z","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":"f0c981aab0e1135a2e1c95ece7ca49b447195b825b6b8153f3a1679263b52325","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-30T15:38:37Z","title_canon_sha256":"242ba8f6ed52bf6036db108ed808663fcfd3d07db237acc77dda57671f0eb2f0"},"schema_version":"1.0","source":{"id":"2006.16908","kind":"arxiv","version":2}},"canonical_sha256":"e3451437ff1478fdf5d75e495853c79d0b3888d4aaeb804122f39c8c4cb10388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3451437ff1478fdf5d75e495853c79d0b3888d4aaeb804122f39c8c4cb10388","first_computed_at":"2026-07-05T02:08:18.249744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:18.249744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C12pkpgMNalRkWdoDyp4MhNGs9efDy6dbXl2x6LlFE23bx9Mgpw/am7Cdo240ixavZKdxdoQN7kbKbsPqIVSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:18.250229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.16908","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60378847d77664b80d05bc8f0f3b3d2b94b729d391663393bc0cd384af27b47b","sha256:9954a874fa0fdaa12b133ee94183528073d4ebfc628ecc0bad1519b5bc538319"],"state_sha256":"1e9789ab21ed40c56b30b296c2db9e2d4d1b711bb7efe696a99bcea13ea9b9e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gT9UE8rEBjNJYqwqRHcjhx2HXM7t7+GXUQt5tla0HaHD9NNN6bC63JekHE7iitFwgCyCyiFr7+EUHE7TExqyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:11:58.301430Z","bundle_sha256":"b4c11a13710c6b309991e6db9dc800c459baad5b5ecbf5c10c26ee840faf74b6"}}