{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3GHV5LHPVRTBJC2FL557OUJZU3","short_pith_number":"pith:3GHV5LHP","canonical_record":{"source":{"id":"2401.12497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T05:43:15Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"d8fe19a25753f9c7b8c6d35a9875416876b28053c052c32f0ac3991bb5d0bbcd","abstract_canon_sha256":"9ce17635ad128149fee606a607c2c65ab13c6d1f3d163b7a0395dbae7d9415ab"},"schema_version":"1.0"},"canonical_sha256":"d98f5eacefac66148b455f7bf75139a6faa9a91980db657d5c30d00fe7e215e5","source":{"kind":"arxiv","id":"2401.12497","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12497","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12497v1","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12497","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"3GHV5LHPVRTB","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"3GHV5LHPVRTBJC2F","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"3GHV5LHP","created_at":"2026-07-05T11:54:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3GHV5LHPVRTBJC2FL557OUJZU3","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T05:43:15Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"d8fe19a25753f9c7b8c6d35a9875416876b28053c052c32f0ac3991bb5d0bbcd","abstract_canon_sha256":"9ce17635ad128149fee606a607c2c65ab13c6d1f3d163b7a0395dbae7d9415ab"},"schema_version":"1.0"},"canonical_sha256":"d98f5eacefac66148b455f7bf75139a6faa9a91980db657d5c30d00fe7e215e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:38.650074Z","signature_b64":"qymhFGVqJfY2SW+HbZRXTDpcnQ8nVANEZJad1a+4/K8XMsyh3olEDHOAW71yYY1zSDBvAaQA8UTY7DkPPkkuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98f5eacefac66148b455f7bf75139a6faa9a91980db657d5c30d00fe7e215e5","last_reissued_at":"2026-07-05T11:54:38.649632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:38.649632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12497","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":"2026-07-05T11:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWpNRNHhFB2ZbaYcnYLBaxDXdMBJVN4pHp78kRzbRtf2QaYzr+ArnmdW3aludaazzdnI7IFUkWFJlzePicK9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:01.745955Z"},"content_sha256":"ce2d79eeebbc7691477b71f1eef5db720261bdb59aabf6ddd2d6a2e4d9659085","schema_version":"1.0","event_id":"sha256:ce2d79eeebbc7691477b71f1eef5db720261bdb59aabf6ddd2d6a2e4d9659085"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3GHV5LHPVRTBJC2FL557OUJZU3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Caroline Wang, Peter Stone, Xuesu Xiao, Yuke Zhu, Zizhao Wang","submitted_at":"2024-01-23T05:43:15Z","abstract_excerpt":"Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for learning the tasks at hand. This paper introduces Causal Bisimulation Modeling (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM leverages and imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12497","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/2401.12497/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":"2026-07-05T11:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wemig6+4Tm4znno+DdeUwEZ+ASJ7XyTK98HqC3jgIcmJNj4pR8kRxUlhMipTm1qR204ACKydAHUQhwdwxoItCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:01.746454Z"},"content_sha256":"fe1fe7d4a80a7e7688ad0dd86e22083d1aa9ac57def516c9979df646791f3438","schema_version":"1.0","event_id":"sha256:fe1fe7d4a80a7e7688ad0dd86e22083d1aa9ac57def516c9979df646791f3438"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GHV5LHPVRTBJC2FL557OUJZU3/bundle.json","state_url":"https://pith.science/pith/3GHV5LHPVRTBJC2FL557OUJZU3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GHV5LHPVRTBJC2FL557OUJZU3/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":"2026-08-08T05:59:01Z","links":{"resolver":"https://pith.science/pith/3GHV5LHPVRTBJC2FL557OUJZU3","bundle":"https://pith.science/pith/3GHV5LHPVRTBJC2FL557OUJZU3/bundle.json","state":"https://pith.science/pith/3GHV5LHPVRTBJC2FL557OUJZU3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GHV5LHPVRTBJC2FL557OUJZU3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3GHV5LHPVRTBJC2FL557OUJZU3","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":"9ce17635ad128149fee606a607c2c65ab13c6d1f3d163b7a0395dbae7d9415ab","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T05:43:15Z","title_canon_sha256":"d8fe19a25753f9c7b8c6d35a9875416876b28053c052c32f0ac3991bb5d0bbcd"},"schema_version":"1.0","source":{"id":"2401.12497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12497","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12497v1","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12497","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"3GHV5LHPVRTB","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"3GHV5LHPVRTBJC2F","created_at":"2026-07-05T11:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"3GHV5LHP","created_at":"2026-07-05T11:54:38Z"}],"graph_snapshots":[{"event_id":"sha256:fe1fe7d4a80a7e7688ad0dd86e22083d1aa9ac57def516c9979df646791f3438","target":"graph","created_at":"2026-07-05T11:54:38Z","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/2401.12497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for learning the tasks at hand. This paper introduces Causal Bisimulation Modeling (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM leverages and imp","authors_text":"Caroline Wang, Peter Stone, Xuesu Xiao, Yuke Zhu, Zizhao Wang","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T05:43:15Z","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12497","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:ce2d79eeebbc7691477b71f1eef5db720261bdb59aabf6ddd2d6a2e4d9659085","target":"record","created_at":"2026-07-05T11:54:38Z","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":"9ce17635ad128149fee606a607c2c65ab13c6d1f3d163b7a0395dbae7d9415ab","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T05:43:15Z","title_canon_sha256":"d8fe19a25753f9c7b8c6d35a9875416876b28053c052c32f0ac3991bb5d0bbcd"},"schema_version":"1.0","source":{"id":"2401.12497","kind":"arxiv","version":1}},"canonical_sha256":"d98f5eacefac66148b455f7bf75139a6faa9a91980db657d5c30d00fe7e215e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d98f5eacefac66148b455f7bf75139a6faa9a91980db657d5c30d00fe7e215e5","first_computed_at":"2026-07-05T11:54:38.649632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:38.649632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qymhFGVqJfY2SW+HbZRXTDpcnQ8nVANEZJad1a+4/K8XMsyh3olEDHOAW71yYY1zSDBvAaQA8UTY7DkPPkkuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:38.650074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce2d79eeebbc7691477b71f1eef5db720261bdb59aabf6ddd2d6a2e4d9659085","sha256:fe1fe7d4a80a7e7688ad0dd86e22083d1aa9ac57def516c9979df646791f3438"],"state_sha256":"81c0d71c81eb49f28279bfbae86a4583558da04a9c422d5a42aa75361c6faf60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QkKVr6psyCSbktSM2TTkyPqmcvrklU0h70BFJ3Y7cTyg1Log9VDnvFlzEldXfOVQxUH46bwaLF94NLvWarobBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:59:01.751673Z","bundle_sha256":"a70f9b3d03827a7463cc1dceeb7b7b82c78f8e213203a5d59f9b37b23ba21eca"}}