{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TAIJAPL7UY4XWHQQ23WFKGJH4Q","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":"0b7ab97b45399f32305bd28f44efa29eb9f54e531dc0e812eafa534be77d4147","cross_cats_sorted":["cs.AI","math.CT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T03:43:47Z","title_canon_sha256":"96f26a0359f72fd3412278b7bdb13fcb8a9d6428f7d8caaa3ff085ae72d363b1"},"schema_version":"1.0","source":{"id":"2606.25357","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25357","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25357v1","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25357","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"TAIJAPL7UY4X","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"TAIJAPL7UY4XWHQQ","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"TAIJAPL7","created_at":"2026-06-25T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:2d583535b10ae59a8d4a6b4074c258f9e01aafa9797a018785d08fc1caab21ee","target":"graph","created_at":"2026-06-25T01:18:03Z","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/2606.25357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavioral structures have been studied in reinforcement learning, including value functions, invariants, bisimulation relations, and behavioral metrics. However, a general principle for determining what structures are provably preserved under state abstraction is still lacking. In this paper, we present a unified framework for defining and analyzing behavioral structures in reinforcement learning. Our framework provides a compositional way to specif","authors_text":"Manuel Baltieri, Yivan Zhang, Ziyan Luo","cross_cats":["cs.AI","math.CT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T03:43:47Z","title":"Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25357","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:bf04b81afdcc82d323c35c080540313c7f989c0a0c08c6d4d6842159439fe4d1","target":"record","created_at":"2026-06-25T01:18:03Z","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":"0b7ab97b45399f32305bd28f44efa29eb9f54e531dc0e812eafa534be77d4147","cross_cats_sorted":["cs.AI","math.CT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T03:43:47Z","title_canon_sha256":"96f26a0359f72fd3412278b7bdb13fcb8a9d6428f7d8caaa3ff085ae72d363b1"},"schema_version":"1.0","source":{"id":"2606.25357","kind":"arxiv","version":1}},"canonical_sha256":"9810903d7fa6397b1e10d6ec551927e43f954ed0cb399cc347d08c520fb87731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9810903d7fa6397b1e10d6ec551927e43f954ed0cb399cc347d08c520fb87731","first_computed_at":"2026-06-25T01:18:03.025247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:03.025247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bopIV1mdOE50KxjO17HYEGZWAhqh+XqYqUKyi4V7YwldLhOQp1RyWPSKLWYTCY18XLCdZbyWXF/gH+VWgpPSDA==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:03.025633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25357","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf04b81afdcc82d323c35c080540313c7f989c0a0c08c6d4d6842159439fe4d1","sha256:2d583535b10ae59a8d4a6b4074c258f9e01aafa9797a018785d08fc1caab21ee"],"state_sha256":"3652cf3ba4987b58cb67ca3aea00f9c1eecf8087401fa0a13083ebe6fbd244d8"}