{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CCHQBM7XCPMXEGK45I5ROH7QFC","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":"5587a1e71a7422233360ac1d6f7fcd59843ffd32d058e311a31e76e964614c91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:18:20Z","title_canon_sha256":"7db9c1b5841d9fc4088c0555aa45acfb5e051deba24eb479b9e2828bdd160ef6"},"schema_version":"1.0","source":{"id":"2605.30928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30928","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30928v1","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30928","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"CCHQBM7XCPMX","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"CCHQBM7XCPMXEGK4","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"CCHQBM7X","created_at":"2026-06-01T01:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:23d2c6768d201e58c79eccd9efa74130c11dc0296acfd3ea96776f722d2935e0","target":"graph","created_at":"2026-06-01T01:03:26Z","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/2605.30928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit behaviors that differ from humans, limiting interpretability and reliability. In this work, we introduce a novel human-like RL framework that predicts action sequences closely aligned with human behaviors while maximizing rewards. Specifically, we encode human demonstrations into macro actions using a hierarchical macro action quantization approach (termed HiMAQ) consisting of two successive levels of vector quantizati","authors_text":"Ali Shah Ali, Fawad Javed Fateh, M. Shaheer Luqman, Murad Popattia, M. Zeeshan Zia, Quoc-Huy Tran, Usman Nizamani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:18:20Z","title":"Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30928","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":"sha256:6c0b1104c0ada5cbd836d774e455dccc2aeb1df1a646f1584dcacf6c627c6288","target":"record","created_at":"2026-06-01T01:03:26Z","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":"5587a1e71a7422233360ac1d6f7fcd59843ffd32d058e311a31e76e964614c91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:18:20Z","title_canon_sha256":"7db9c1b5841d9fc4088c0555aa45acfb5e051deba24eb479b9e2828bdd160ef6"},"schema_version":"1.0","source":{"id":"2605.30928","kind":"arxiv","version":1}},"canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","first_computed_at":"2026-06-01T01:03:26.397144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:26.397144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uOfZQRvzu/orUADeyKxJKGJXWvz9sP4imHuRqNUWSx2XatkLQOkvgBgdCrzhWocuOy1HYqSNV1xYfMxmapRbDA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:26.398085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c0b1104c0ada5cbd836d774e455dccc2aeb1df1a646f1584dcacf6c627c6288","sha256:23d2c6768d201e58c79eccd9efa74130c11dc0296acfd3ea96776f722d2935e0"],"state_sha256":"396634f1dce85a66897f26089689a70122dcd00f0e7e528b373272b826f5fcf1"}