{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GQWU3GMC6YCAXJWCIIPY4SPUXJ","short_pith_number":"pith:GQWU3GMC","canonical_record":{"source":{"id":"2106.08229","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T14:24:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55da2b57108cdb3f04b80c745e682786bd748442928c1854e8edf283b33df993","abstract_canon_sha256":"2a4404b07c9b1a6da8286c9dea90b3a10c4707b57149803ff9198543dfc4ed9d"},"schema_version":"1.0"},"canonical_sha256":"342d4d9982f6040ba6c2421f8e49f4ba76f8c88966f15f2e1f76cffb34cd0d47","source":{"kind":"arxiv","id":"2106.08229","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08229","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08229v4","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08229","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"pith_short_12","alias_value":"GQWU3GMC6YCA","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"pith_short_16","alias_value":"GQWU3GMC6YCAXJWC","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"pith_short_8","alias_value":"GQWU3GMC","created_at":"2026-07-05T03:50:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GQWU3GMC6YCAXJWCIIPY4SPUXJ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.08229","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T14:24:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55da2b57108cdb3f04b80c745e682786bd748442928c1854e8edf283b33df993","abstract_canon_sha256":"2a4404b07c9b1a6da8286c9dea90b3a10c4707b57149803ff9198543dfc4ed9d"},"schema_version":"1.0"},"canonical_sha256":"342d4d9982f6040ba6c2421f8e49f4ba76f8c88966f15f2e1f76cffb34cd0d47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:35.470193Z","signature_b64":"GsHn8DMH5ykR0UVYB13hVQemYUdDIIs2hyQRjarRNmdJ0FHTJzQenGd7fLFnIlZyAOBK7MwHoSFo0sI8eE0wAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342d4d9982f6040ba6c2421f8e49f4ba76f8c88966f15f2e1f76cffb34cd0d47","last_reissued_at":"2026-07-05T03:50:35.469709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:35.469709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.08229","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":"2026-07-05T03:50:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPrfm3q1EJyaN9pmVAvsrZErsv+fiAtjRTZGiOG4bXUUOb55GM06w6+v7cuVpoc9xQYzsZS8Wv/Z2OffQl5HBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:36:47.662029Z"},"content_sha256":"f013106b04453a1684cc7dbb2aa7e258025513a0767cbbeb534e0847ad02a8c5","schema_version":"1.0","event_id":"sha256:f013106b04453a1684cc7dbb2aa7e258025513a0767cbbeb534e0847ad02a8c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GQWU3GMC6YCAXJWCIIPY4SPUXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mark Rowland, Pablo Samuel Castro, Prakash Panangaden, Tyler Kastner","submitted_at":"2021-06-03T14:24:12Z","abstract_excerpt":"We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an effective means of shaping the learnt representations of deep reinforcement learning agents. While existing notions of state similarity are typically difficult to learn at scale due to high computational cost and lack of sample-based algorithms, our newly-proposed distance addresses both of these issues. In addition to providing detailed theoretical analysis, we provide empirical evidence that learning this distance alongside the value function yields structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08229","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.08229/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":"2026-07-05T03:50:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2yR1gkkaWp3kDYtOj5SLsGT4quWliC/+bAxaJ7TLOC1Q9/BhvAvWFioT3kSYxABVjqk5Y7lxKuSacNv7jmsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:36:47.662516Z"},"content_sha256":"e9e0c4bc99336622eeab7214dab3d6435d8a4d33748414a688986538777972fb","schema_version":"1.0","event_id":"sha256:e9e0c4bc99336622eeab7214dab3d6435d8a4d33748414a688986538777972fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ/bundle.json","state_url":"https://pith.science/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ/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":"2026-08-04T22:36:47Z","links":{"resolver":"https://pith.science/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ","bundle":"https://pith.science/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ/bundle.json","state":"https://pith.science/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQWU3GMC6YCAXJWCIIPY4SPUXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GQWU3GMC6YCAXJWCIIPY4SPUXJ","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":"2a4404b07c9b1a6da8286c9dea90b3a10c4707b57149803ff9198543dfc4ed9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T14:24:12Z","title_canon_sha256":"55da2b57108cdb3f04b80c745e682786bd748442928c1854e8edf283b33df993"},"schema_version":"1.0","source":{"id":"2106.08229","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08229","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08229v4","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08229","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"pith_short_12","alias_value":"GQWU3GMC6YCA","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"pith_short_16","alias_value":"GQWU3GMC6YCAXJWC","created_at":"2026-07-05T03:50:35Z"},{"alias_kind":"pith_short_8","alias_value":"GQWU3GMC","created_at":"2026-07-05T03:50:35Z"}],"graph_snapshots":[{"event_id":"sha256:e9e0c4bc99336622eeab7214dab3d6435d8a4d33748414a688986538777972fb","target":"graph","created_at":"2026-07-05T03:50:35Z","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/2106.08229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new behavioural distance over the state space of a Markov decision process, and demonstrate the use of this distance as an effective means of shaping the learnt representations of deep reinforcement learning agents. While existing notions of state similarity are typically difficult to learn at scale due to high computational cost and lack of sample-based algorithms, our newly-proposed distance addresses both of these issues. In addition to providing detailed theoretical analysis, we provide empirical evidence that learning this distance alongside the value function yields structur","authors_text":"Mark Rowland, Pablo Samuel Castro, Prakash Panangaden, Tyler Kastner","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T14:24:12Z","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08229","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:f013106b04453a1684cc7dbb2aa7e258025513a0767cbbeb534e0847ad02a8c5","target":"record","created_at":"2026-07-05T03:50:35Z","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":"2a4404b07c9b1a6da8286c9dea90b3a10c4707b57149803ff9198543dfc4ed9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T14:24:12Z","title_canon_sha256":"55da2b57108cdb3f04b80c745e682786bd748442928c1854e8edf283b33df993"},"schema_version":"1.0","source":{"id":"2106.08229","kind":"arxiv","version":4}},"canonical_sha256":"342d4d9982f6040ba6c2421f8e49f4ba76f8c88966f15f2e1f76cffb34cd0d47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"342d4d9982f6040ba6c2421f8e49f4ba76f8c88966f15f2e1f76cffb34cd0d47","first_computed_at":"2026-07-05T03:50:35.469709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:50:35.469709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GsHn8DMH5ykR0UVYB13hVQemYUdDIIs2hyQRjarRNmdJ0FHTJzQenGd7fLFnIlZyAOBK7MwHoSFo0sI8eE0wAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:50:35.470193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08229","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f013106b04453a1684cc7dbb2aa7e258025513a0767cbbeb534e0847ad02a8c5","sha256:e9e0c4bc99336622eeab7214dab3d6435d8a4d33748414a688986538777972fb"],"state_sha256":"48eaa8598b17fa488dcb3b4c8e1d31395dd195c8074b839527a7b0f68008e64d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P0haePjpee6hoV8mYHuxUYDIEpkMcSAyfCIzF2igoCHwVK0Lc9vRJlyURQJqrPSdWTFEPlqm1u1dryWfJOvvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:36:47.666076Z","bundle_sha256":"1d964f94206ed194aafc70a37d00f7af88ecfcea1c8deeddf4ebf9d7b38671c4"}}