{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:22SKRVBN6JPMXE7TRXT7KERWRX","short_pith_number":"pith:22SKRVBN","canonical_record":{"source":{"id":"2605.14246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T01:23:09Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"ea214f43eddd2a9618adef28a0e04e8a22aa30150bcb7982081b855fad359598","abstract_canon_sha256":"3f200740c745531f54a7d7846d87a31d780daab9d32338fab196a8ac00834794"},"schema_version":"1.0"},"canonical_sha256":"d6a4a8d42df25ecb93f38de7f512368de2cb8bbc79db99e0eeb77cc4f1fb830c","source":{"kind":"arxiv","id":"2605.14246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14246","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14246v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14246","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"22SKRVBN6JPM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"22SKRVBN6JPMXE7T","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"22SKRVBN","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:22SKRVBN6JPMXE7TRXT7KERWRX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T01:23:09Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"ea214f43eddd2a9618adef28a0e04e8a22aa30150bcb7982081b855fad359598","abstract_canon_sha256":"3f200740c745531f54a7d7846d87a31d780daab9d32338fab196a8ac00834794"},"schema_version":"1.0"},"canonical_sha256":"d6a4a8d42df25ecb93f38de7f512368de2cb8bbc79db99e0eeb77cc4f1fb830c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.609014Z","signature_b64":"eRod+HirrQxtKKtVRn5qd2NfQ1bqsExmXU8WtzJD9R2duvqDvxl4AS1TaSZ7bf0CQaysDb9esnHlmP34VoUYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a4a8d42df25ecb93f38de7f512368de2cb8bbc79db99e0eeb77cc4f1fb830c","last_reissued_at":"2026-05-17T23:39:10.608575Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.608575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14246","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":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ao05m3VQ97xKb9KBDOhMU36SuqHKgpHnRLsoZhBJgu2TITugfWqgCG1xuOiGttN8tLsnaqOm2mvH7KBjc4EZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:02:03.762890Z"},"content_sha256":"0319d8bc211c9be4f7ce77f81ebbfa7a7801035275cc2def5ab30165e456a846","schema_version":"1.0","event_id":"sha256:0319d8bc211c9be4f7ce77f81ebbfa7a7801035275cc2def5ab30165e456a846"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:22SKRVBN6JPMXE7TRXT7KERWRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A learned action-conditioned predictor of near-term safety violations gates value estimates to approximate risk-sensitive control under partial observability.","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Heng Huang, Tao Wang, Xugui Zhou, Yanfu Zhang, Yin-Jen Chen, Yushen Liu, Ziyi Chen","submitted_at":"2026-05-14T01:23:09Z","abstract_excerpt":"Many safety-critical control problems are modeled as risk-sensitive partially observable Markov decision processes, where the controller must make decisions from incomplete observations while balancing task performance against safety risk. Although belief-space planning provides a principled solution, maintaining and planning over beliefs can be computationally costly and sensitive to model specification in practical domains. We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability. The method constructs a compact finite-hi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The method improves overall glycemic tradeoffs and substantially reduces runtime relative to a belief-space planning baseline; on Safety-Gym it achieves a more favorable reward-cost balance than unconstrained RL and several standard safe-RL baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a compact finite-history proxy state plus a learned action-conditioned predictor of near-term safety violation is sufficient to produce effective risk-sensitive decisions under partial observability.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Action-conditioned near-term risk prediction gates optimistic and conservative value estimates in RL to approximate risk-sensitive POMDP control, yielding better safety-performance tradeoffs with lower runtime than belief planning baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A learned action-conditioned predictor of near-term safety violations gates value estimates to approximate risk-sensitive control under partial observability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"da3983a19118da38cb1c1d65d48abc5d362be406f7314533e91fb93b11cceed0"},"source":{"id":"2605.14246","kind":"arxiv","version":1},"verdict":{"id":"dd18a9dc-bf75-4175-aa27-94ce3be932f3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:48:00.155013Z","strongest_claim":"The method improves overall glycemic tradeoffs and substantially reduces runtime relative to a belief-space planning baseline; on Safety-Gym it achieves a more favorable reward-cost balance than unconstrained RL and several standard safe-RL baselines.","one_line_summary":"Action-conditioned near-term risk prediction gates optimistic and conservative value estimates in RL to approximate risk-sensitive POMDP control, yielding better safety-performance tradeoffs with lower runtime than belief planning baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a compact finite-history proxy state plus a learned action-conditioned predictor of near-term safety violation is sufficient to produce effective risk-sensitive decisions under partial observability.","pith_extraction_headline":"A learned action-conditioned predictor of near-term safety violations gates value estimates to approximate risk-sensitive control under partial observability."},"references":{"count":43,"sample":[{"doi":"","year":2017,"title":"Constrained policy optimization","work_id":"ace446d3-1647-4c52-860a-71a3c7d98d0e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Constrained policy optimization","work_id":"dbc1e043-d69a-4f56-9bf8-4642cb64c654","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"A distributional perspective on rein- forcement learning","work_id":"f0303492-1604-45c4-aac5-a66a39390990","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Wayne Bequette, Darrell M","work_id":"f14324de-0b19-4e09-9997-3338f9d9c47c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Safe reinforcement learning via shielding under par- tial observability","work_id":"a05af2ae-790a-4f85-bd85-701aeed62ba9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":43,"snapshot_sha256":"129f3291e446d23a0fe0e0eed55fa3fd41459e003687e0398f51f4ebe05a7a67","internal_anchors":3},"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":"dd18a9dc-bf75-4175-aa27-94ce3be932f3"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R23Dslb3wegm++4f2RHPFOHV9Iq8cBhygDUN/gmOHskgwrCw8qwMUqCdcQ5dyWTNPMcBDg4IyMMPdnetw5f/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:02:03.763916Z"},"content_sha256":"e8219c9f5e021106183fdf9ce72e731fe320041188ec7e1e36792ab67d0f11ca","schema_version":"1.0","event_id":"sha256:e8219c9f5e021106183fdf9ce72e731fe320041188ec7e1e36792ab67d0f11ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/22SKRVBN6JPMXE7TRXT7KERWRX/bundle.json","state_url":"https://pith.science/pith/22SKRVBN6JPMXE7TRXT7KERWRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/22SKRVBN6JPMXE7TRXT7KERWRX/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":"2026-05-27T10:02:03Z","links":{"resolver":"https://pith.science/pith/22SKRVBN6JPMXE7TRXT7KERWRX","bundle":"https://pith.science/pith/22SKRVBN6JPMXE7TRXT7KERWRX/bundle.json","state":"https://pith.science/pith/22SKRVBN6JPMXE7TRXT7KERWRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/22SKRVBN6JPMXE7TRXT7KERWRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:22SKRVBN6JPMXE7TRXT7KERWRX","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":"3f200740c745531f54a7d7846d87a31d780daab9d32338fab196a8ac00834794","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T01:23:09Z","title_canon_sha256":"ea214f43eddd2a9618adef28a0e04e8a22aa30150bcb7982081b855fad359598"},"schema_version":"1.0","source":{"id":"2605.14246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14246","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14246v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14246","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"22SKRVBN6JPM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"22SKRVBN6JPMXE7T","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"22SKRVBN","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e8219c9f5e021106183fdf9ce72e731fe320041188ec7e1e36792ab67d0f11ca","target":"graph","created_at":"2026-05-17T23:39:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The method improves overall glycemic tradeoffs and substantially reduces runtime relative to a belief-space planning baseline; on Safety-Gym it achieves a more favorable reward-cost balance than unconstrained RL and several standard safe-RL baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a compact finite-history proxy state plus a learned action-conditioned predictor of near-term safety violation is sufficient to produce effective risk-sensitive decisions under partial observability."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Action-conditioned near-term risk prediction gates optimistic and conservative value estimates in RL to approximate risk-sensitive POMDP control, yielding better safety-performance tradeoffs with lower runtime than belief planning baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A learned action-conditioned predictor of near-term safety violations gates value estimates to approximate risk-sensitive control under partial observability."}],"snapshot_sha256":"da3983a19118da38cb1c1d65d48abc5d362be406f7314533e91fb93b11cceed0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Many safety-critical control problems are modeled as risk-sensitive partially observable Markov decision processes, where the controller must make decisions from incomplete observations while balancing task performance against safety risk. Although belief-space planning provides a principled solution, maintaining and planning over beliefs can be computationally costly and sensitive to model specification in practical domains. We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability. The method constructs a compact finite-hi","authors_text":"Heng Huang, Tao Wang, Xugui Zhou, Yanfu Zhang, Yin-Jen Chen, Yushen Liu, Ziyi Chen","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"A learned action-conditioned predictor of near-term safety violations gates value estimates to approximate risk-sensitive control under partial observability.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T01:23:09Z","title":"Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability"},"references":{"count":43,"internal_anchors":3,"resolved_work":43,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Constrained policy optimization","work_id":"ace446d3-1647-4c52-860a-71a3c7d98d0e","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Constrained policy optimization","work_id":"dbc1e043-d69a-4f56-9bf8-4642cb64c654","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A distributional perspective on rein- forcement learning","work_id":"f0303492-1604-45c4-aac5-a66a39390990","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Wayne Bequette, Darrell M","work_id":"f14324de-0b19-4e09-9997-3338f9d9c47c","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Safe reinforcement learning via shielding under par- tial observability","work_id":"a05af2ae-790a-4f85-bd85-701aeed62ba9","year":2023}],"snapshot_sha256":"129f3291e446d23a0fe0e0eed55fa3fd41459e003687e0398f51f4ebe05a7a67"},"source":{"id":"2605.14246","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:48:00.155013Z","id":"dd18a9dc-bf75-4175-aa27-94ce3be932f3","model_set":{"reader":"grok-4.3"},"one_line_summary":"Action-conditioned near-term risk prediction gates optimistic and conservative value estimates in RL to approximate risk-sensitive POMDP control, yielding better safety-performance tradeoffs with lower runtime than belief planning baselines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A learned action-conditioned predictor of near-term safety violations gates value estimates to approximate risk-sensitive control under partial observability.","strongest_claim":"The method improves overall glycemic tradeoffs and substantially reduces runtime relative to a belief-space planning baseline; on Safety-Gym it achieves a more favorable reward-cost balance than unconstrained RL and several standard safe-RL baselines.","weakest_assumption":"That a compact finite-history proxy state plus a learned action-conditioned predictor of near-term safety violation is sufficient to produce effective risk-sensitive decisions under partial observability."}},"verdict_id":"dd18a9dc-bf75-4175-aa27-94ce3be932f3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0319d8bc211c9be4f7ce77f81ebbfa7a7801035275cc2def5ab30165e456a846","target":"record","created_at":"2026-05-17T23:39:10Z","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":"3f200740c745531f54a7d7846d87a31d780daab9d32338fab196a8ac00834794","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T01:23:09Z","title_canon_sha256":"ea214f43eddd2a9618adef28a0e04e8a22aa30150bcb7982081b855fad359598"},"schema_version":"1.0","source":{"id":"2605.14246","kind":"arxiv","version":1}},"canonical_sha256":"d6a4a8d42df25ecb93f38de7f512368de2cb8bbc79db99e0eeb77cc4f1fb830c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6a4a8d42df25ecb93f38de7f512368de2cb8bbc79db99e0eeb77cc4f1fb830c","first_computed_at":"2026-05-17T23:39:10.608575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.608575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eRod+HirrQxtKKtVRn5qd2NfQ1bqsExmXU8WtzJD9R2duvqDvxl4AS1TaSZ7bf0CQaysDb9esnHlmP34VoUYBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.609014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0319d8bc211c9be4f7ce77f81ebbfa7a7801035275cc2def5ab30165e456a846","sha256:e8219c9f5e021106183fdf9ce72e731fe320041188ec7e1e36792ab67d0f11ca"],"state_sha256":"6247c25785fe644babd55c24dca0e3a72f5f103af4b18f6a3d1d909b59dfb3a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LAp8YE+hOv6gatjX92wz0NpR/2g/FxgzyCksKsbb6x/boXCsMgZbD/SWheRlVvR8rHWpPpS/A7C8YCYiMBuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:02:03.768999Z","bundle_sha256":"6be6273283324dc7f7c3e8af7dcc2b1dac2bf5f2dc0864d53e7d21b3a70b91d9"}}