{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CCHQBM7XCPMXEGK45I5ROH7QFC","short_pith_number":"pith:CCHQBM7X","canonical_record":{"source":{"id":"2605.30928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"7db9c1b5841d9fc4088c0555aa45acfb5e051deba24eb479b9e2828bdd160ef6","abstract_canon_sha256":"5587a1e71a7422233360ac1d6f7fcd59843ffd32d058e311a31e76e964614c91"},"schema_version":"1.0"},"canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","source":{"kind":"arxiv","id":"2605.30928","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CCHQBM7XCPMXEGK45I5ROH7QFC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"7db9c1b5841d9fc4088c0555aa45acfb5e051deba24eb479b9e2828bdd160ef6","abstract_canon_sha256":"5587a1e71a7422233360ac1d6f7fcd59843ffd32d058e311a31e76e964614c91"},"schema_version":"1.0"},"canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:26.398085Z","signature_b64":"uOfZQRvzu/orUADeyKxJKGJXWvz9sP4imHuRqNUWSx2XatkLQOkvgBgdCrzhWocuOy1HYqSNV1xYfMxmapRbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"108f00b3f713d972195cea3b171ff028a88a7ee6c5c9120ad41f283ec36df3ac","last_reissued_at":"2026-06-01T01:03:26.397144Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:26.397144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30928","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":"2026-06-01T01:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Afffw6iRyVaHzxy4sxyFIG8OK5NCpa9AwaiA7wPXfmEgxA9Wt/xY8FQAB7ycFeY1dFDQLGwO0hrwV11FGDdDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:01:31.971697Z"},"content_sha256":"6c0b1104c0ada5cbd836d774e455dccc2aeb1df1a646f1584dcacf6c627c6288","schema_version":"1.0","event_id":"sha256:6c0b1104c0ada5cbd836d774e455dccc2aeb1df1a646f1584dcacf6c627c6288"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CCHQBM7XCPMXEGK45I5ROH7QFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Shah Ali, Fawad Javed Fateh, M. Shaheer Luqman, Murad Popattia, M. Zeeshan Zia, Quoc-Huy Tran, Usman Nizamani","submitted_at":"2026-05-29T07:18:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30928","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/2605.30928/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":"2026-06-01T01:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cE8WljiQCXT5uARqDh4lrZcW6PLPyGVaWGRVYtnosXfwyg0orc/FjzxuON9nrsVzkusX/m/qDjABHHzazzYBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:01:31.972114Z"},"content_sha256":"23d2c6768d201e58c79eccd9efa74130c11dc0296acfd3ea96776f722d2935e0","schema_version":"1.0","event_id":"sha256:23d2c6768d201e58c79eccd9efa74130c11dc0296acfd3ea96776f722d2935e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/bundle.json","state_url":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/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":"2026-06-02T04:01:31Z","links":{"resolver":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC","bundle":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/bundle.json","state":"https://pith.science/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCHQBM7XCPMXEGK45I5ROH7QFC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKNBQ/QKuYc6viBiwg32ALe58HNULk/416XJbO/UHaDs4L2sZcsp0BkDaDa3ZDr08QRt5+73kLghmBLzLemsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:01:31.974249Z","bundle_sha256":"df43944c1f5a4abea84bbfb713b5cb482f73d41658e7328b65d35f4ba2819782"}}