{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UDS5CUAECK2Y3DGKCHCQAJU332","short_pith_number":"pith:UDS5CUAE","canonical_record":{"source":{"id":"2512.05291","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-04T22:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"89dd86c7a2e770b0240e42b7c107457898cca68a166929713cddf8c6b4a99d9e","abstract_canon_sha256":"fe1be019743efd3f1e73f5d1d7f15f25781f843cbe4b5847eaa95522a991aa28"},"schema_version":"1.0"},"canonical_sha256":"a0e5d1500412b58d8cca11c500269bde87d02622f0f834d2990d69defc5b1a37","source":{"kind":"arxiv","id":"2512.05291","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.05291","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2512.05291v3","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05291","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"UDS5CUAECK2Y","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"UDS5CUAECK2Y3DGK","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"UDS5CUAE","created_at":"2026-06-08T01:03:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UDS5CUAECK2Y3DGKCHCQAJU332","target":"record","payload":{"canonical_record":{"source":{"id":"2512.05291","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-04T22:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"89dd86c7a2e770b0240e42b7c107457898cca68a166929713cddf8c6b4a99d9e","abstract_canon_sha256":"fe1be019743efd3f1e73f5d1d7f15f25781f843cbe4b5847eaa95522a991aa28"},"schema_version":"1.0"},"canonical_sha256":"a0e5d1500412b58d8cca11c500269bde87d02622f0f834d2990d69defc5b1a37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:52.507658Z","signature_b64":"GIyRsjxWtVLxueVpQ5dEVVm8AlAFrUJl2rYpacVI/vyVOP5Am0jhFCq+HkHgrKtu7L6TTpaqmwNY7o2oPn+/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e5d1500412b58d8cca11c500269bde87d02622f0f834d2990d69defc5b1a37","last_reissued_at":"2026-06-08T01:03:52.506647Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:52.506647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.05291","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/c4v1vwBxP4kDcGcZjLbWqqcnFUyHIhqnvLTOM8uyDd4qNHAmr+uAN7ctxCujkkaS1BSwZopfH63FwUr9Ri0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:21:12.842476Z"},"content_sha256":"f9286e13213712a20bfe369f945d5b86bd37e3302c6c6e1b37fd2e36ee3b220c","schema_version":"1.0","event_id":"sha256:f9286e13213712a20bfe369f945d5b86bd37e3302c6c6e1b37fd2e36ee3b220c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UDS5CUAECK2Y3DGKCHCQAJU332","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hangguan Shan, Na Li, Wei Ni, Wenjie Zhang, Xinyu Li","submitted_at":"2025-12-04T22:28:43Z","abstract_excerpt":"Actor-critic (AC) methods are a cornerstone of reinforcement learning (RL) but offer limited interpretability. Current explainable RL methods seldom use state attributions to assist training. Rather, they treat all state features equally, thereby neglecting the heterogeneous impacts of individual state dimensions on the reward. We propose RKHS-SHAP-based Advanced Actor-Critic (RSA2C), an attribution-aware, kernelized, two-timescale AC algorithm, including Actor, Value Critic, and Advantage Critic. The Actor is instantiated in a vector-valued reproducing kernel Hilbert space (RKHS) with a Mahal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05291","kind":"arxiv","version":3},"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/2512.05291/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":"2026-06-08T01:03:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KlH36toiXLYdGeziOyUL85Tk5pOWgdH4bYBeEht4vlELbjw0SFEq0AWs2fsvOWcIUNCLmJO6ZGa33/X+R1JSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:21:12.843462Z"},"content_sha256":"87ba909e639c3bc5cc04e7240a4b85d940e03104a588b91212907dae5727099f","schema_version":"1.0","event_id":"sha256:87ba909e639c3bc5cc04e7240a4b85d940e03104a588b91212907dae5727099f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDS5CUAECK2Y3DGKCHCQAJU332/bundle.json","state_url":"https://pith.science/pith/UDS5CUAECK2Y3DGKCHCQAJU332/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDS5CUAECK2Y3DGKCHCQAJU332/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":"2026-08-17T00:21:12Z","links":{"resolver":"https://pith.science/pith/UDS5CUAECK2Y3DGKCHCQAJU332","bundle":"https://pith.science/pith/UDS5CUAECK2Y3DGKCHCQAJU332/bundle.json","state":"https://pith.science/pith/UDS5CUAECK2Y3DGKCHCQAJU332/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDS5CUAECK2Y3DGKCHCQAJU332/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UDS5CUAECK2Y3DGKCHCQAJU332","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":"fe1be019743efd3f1e73f5d1d7f15f25781f843cbe4b5847eaa95522a991aa28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-04T22:28:43Z","title_canon_sha256":"89dd86c7a2e770b0240e42b7c107457898cca68a166929713cddf8c6b4a99d9e"},"schema_version":"1.0","source":{"id":"2512.05291","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.05291","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2512.05291v3","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05291","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"UDS5CUAECK2Y","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"UDS5CUAECK2Y3DGK","created_at":"2026-06-08T01:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"UDS5CUAE","created_at":"2026-06-08T01:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:87ba909e639c3bc5cc04e7240a4b85d940e03104a588b91212907dae5727099f","target":"graph","created_at":"2026-06-08T01:03:52Z","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/2512.05291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic (AC) methods are a cornerstone of reinforcement learning (RL) but offer limited interpretability. Current explainable RL methods seldom use state attributions to assist training. Rather, they treat all state features equally, thereby neglecting the heterogeneous impacts of individual state dimensions on the reward. We propose RKHS-SHAP-based Advanced Actor-Critic (RSA2C), an attribution-aware, kernelized, two-timescale AC algorithm, including Actor, Value Critic, and Advantage Critic. The Actor is instantiated in a vector-valued reproducing kernel Hilbert space (RKHS) with a Mahal","authors_text":"Hangguan Shan, Na Li, Wei Ni, Wenjie Zhang, Xinyu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-04T22:28:43Z","title":"SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05291","kind":"arxiv","version":3},"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:f9286e13213712a20bfe369f945d5b86bd37e3302c6c6e1b37fd2e36ee3b220c","target":"record","created_at":"2026-06-08T01:03:52Z","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":"fe1be019743efd3f1e73f5d1d7f15f25781f843cbe4b5847eaa95522a991aa28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-04T22:28:43Z","title_canon_sha256":"89dd86c7a2e770b0240e42b7c107457898cca68a166929713cddf8c6b4a99d9e"},"schema_version":"1.0","source":{"id":"2512.05291","kind":"arxiv","version":3}},"canonical_sha256":"a0e5d1500412b58d8cca11c500269bde87d02622f0f834d2990d69defc5b1a37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0e5d1500412b58d8cca11c500269bde87d02622f0f834d2990d69defc5b1a37","first_computed_at":"2026-06-08T01:03:52.506647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:52.506647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GIyRsjxWtVLxueVpQ5dEVVm8AlAFrUJl2rYpacVI/vyVOP5Am0jhFCq+HkHgrKtu7L6TTpaqmwNY7o2oPn+/Dg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:52.507658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.05291","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9286e13213712a20bfe369f945d5b86bd37e3302c6c6e1b37fd2e36ee3b220c","sha256:87ba909e639c3bc5cc04e7240a4b85d940e03104a588b91212907dae5727099f"],"state_sha256":"c91f1ca6571eec8936ff953497dea446b7d14e6ed7a370f3634d0ffbfa6894de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/Qiqox3rFFRIuiJ0h3RzzGFx6lPlDpgMhQ8IeQ+VOYC+FqORH43fMQfrndls77XCxxqJPiGC0mCy3TdjUDtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T00:21:12.855344Z","bundle_sha256":"a109367a35a7563043655f488b1d9dcdb8aea16c06a04da369cfb57eef33d400"}}