{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2PUXTTXPNHU5KZAFJGP4LHDYZX","short_pith_number":"pith:2PUXTTXP","canonical_record":{"source":{"id":"2412.04327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T16:42:45Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"0f0b0a11c084539065423bb72d76cf8bf181cd42aff729d8eed68a32887a0c46","abstract_canon_sha256":"5e4ec47eb4e493cdbbcbe0bc8ff23f191d17c2d8dcc66d610500139e38ed93f4"},"schema_version":"1.0"},"canonical_sha256":"d3e979ceef69e9d56405499fc59c78cde361e5b4a29ee3acb1d0fd8fb811bcca","source":{"kind":"arxiv","id":"2412.04327","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04327","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04327v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04327","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"2PUXTTXPNHU5","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"2PUXTTXPNHU5KZAF","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"2PUXTTXP","created_at":"2026-07-05T09:45:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2PUXTTXPNHU5KZAFJGP4LHDYZX","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T16:42:45Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"0f0b0a11c084539065423bb72d76cf8bf181cd42aff729d8eed68a32887a0c46","abstract_canon_sha256":"5e4ec47eb4e493cdbbcbe0bc8ff23f191d17c2d8dcc66d610500139e38ed93f4"},"schema_version":"1.0"},"canonical_sha256":"d3e979ceef69e9d56405499fc59c78cde361e5b4a29ee3acb1d0fd8fb811bcca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:02.501531Z","signature_b64":"CHZPWhF8GD0YIviLp2dflGWKcJgCvrJv6gMM2jQX/6dbhoTTqCCrZ+zs8BbrbV8Vp/WTy0H1mAATvN4aO0vBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e979ceef69e9d56405499fc59c78cde361e5b4a29ee3acb1d0fd8fb811bcca","last_reissued_at":"2026-07-05T09:45:02.501129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:02.501129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04327","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":"2026-07-05T09:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AsMobNDKb8lKczK54g3yZATDrYGiZZhjPcsCvjwQllQvmA1rNZwdVthuoyb5fHzB7F6YoOfXeSHD/x44HOEABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:16:04.206512Z"},"content_sha256":"535b07afafe6bb59094b55e99613d672d4dbe3c87b8efc2421c44a7227afd1aa","schema_version":"1.0","event_id":"sha256:535b07afafe6bb59094b55e99613d672d4dbe3c87b8efc2421c44a7227afd1aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2PUXTTXPNHU5KZAFJGP4LHDYZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Mapping for Reinforcement Learning in Continuous Environments with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alberto L. Sangiovanni-Vincentelli, Lukas Dirnberger, Marco Caccamo, Mirco Theile, Raphael Trumpp","submitted_at":"2024-12-05T16:42:45Z","abstract_excerpt":"Deep reinforcement learning (DRL) has had success across various domains, but applying it to environments with constraints remains challenging due to poor sample efficiency and slow convergence. Recent literature explored incorporating model knowledge to mitigate these problems, particularly through the use of models that assess the feasibility of proposed actions. However, integrating feasibility models efficiently into DRL pipelines in environments with continuous action spaces is non-trivial. We propose a novel DRL training strategy utilizing action mapping that leverages feasibility models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04327","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/2412.04327/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":"2026-07-05T09:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hsH3d2Gyk7CvRjgatHwhJ/Y8ZAKKlc/DXQVSJVLBHWFF6wXo1U5NtwRGZ8OSIcn5FdRnh+Wyaq4jsTf2oTt3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:16:04.207062Z"},"content_sha256":"dbd500977736bca1ac12010c863322e7efd3bf774289d3a067a0d11930bf8e2c","schema_version":"1.0","event_id":"sha256:dbd500977736bca1ac12010c863322e7efd3bf774289d3a067a0d11930bf8e2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX/bundle.json","state_url":"https://pith.science/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX/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":"2026-08-12T16:16:04Z","links":{"resolver":"https://pith.science/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX","bundle":"https://pith.science/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX/bundle.json","state":"https://pith.science/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PUXTTXPNHU5KZAFJGP4LHDYZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2PUXTTXPNHU5KZAFJGP4LHDYZX","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":"5e4ec47eb4e493cdbbcbe0bc8ff23f191d17c2d8dcc66d610500139e38ed93f4","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T16:42:45Z","title_canon_sha256":"0f0b0a11c084539065423bb72d76cf8bf181cd42aff729d8eed68a32887a0c46"},"schema_version":"1.0","source":{"id":"2412.04327","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04327","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04327v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04327","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"2PUXTTXPNHU5","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"2PUXTTXPNHU5KZAF","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"2PUXTTXP","created_at":"2026-07-05T09:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:dbd500977736bca1ac12010c863322e7efd3bf774289d3a067a0d11930bf8e2c","target":"graph","created_at":"2026-07-05T09:45:02Z","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/2412.04327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has had success across various domains, but applying it to environments with constraints remains challenging due to poor sample efficiency and slow convergence. Recent literature explored incorporating model knowledge to mitigate these problems, particularly through the use of models that assess the feasibility of proposed actions. However, integrating feasibility models efficiently into DRL pipelines in environments with continuous action spaces is non-trivial. We propose a novel DRL training strategy utilizing action mapping that leverages feasibility models","authors_text":"Alberto L. Sangiovanni-Vincentelli, Lukas Dirnberger, Marco Caccamo, Mirco Theile, Raphael Trumpp","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T16:42:45Z","title":"Action Mapping for Reinforcement Learning in Continuous Environments with Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04327","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":"sha256:535b07afafe6bb59094b55e99613d672d4dbe3c87b8efc2421c44a7227afd1aa","target":"record","created_at":"2026-07-05T09:45:02Z","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":"5e4ec47eb4e493cdbbcbe0bc8ff23f191d17c2d8dcc66d610500139e38ed93f4","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T16:42:45Z","title_canon_sha256":"0f0b0a11c084539065423bb72d76cf8bf181cd42aff729d8eed68a32887a0c46"},"schema_version":"1.0","source":{"id":"2412.04327","kind":"arxiv","version":1}},"canonical_sha256":"d3e979ceef69e9d56405499fc59c78cde361e5b4a29ee3acb1d0fd8fb811bcca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3e979ceef69e9d56405499fc59c78cde361e5b4a29ee3acb1d0fd8fb811bcca","first_computed_at":"2026-07-05T09:45:02.501129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:02.501129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CHZPWhF8GD0YIviLp2dflGWKcJgCvrJv6gMM2jQX/6dbhoTTqCCrZ+zs8BbrbV8Vp/WTy0H1mAATvN4aO0vBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:02.501531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04327","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:535b07afafe6bb59094b55e99613d672d4dbe3c87b8efc2421c44a7227afd1aa","sha256:dbd500977736bca1ac12010c863322e7efd3bf774289d3a067a0d11930bf8e2c"],"state_sha256":"ac69139c35ffea9527296f0230b86463d15885c02cb5bc8e8466a9eb49950a7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPTfcM61yZvcDKYnj2VPMy1zuNG+Ck8Z7PMgb5bv2dQx7o8bWC+bfrJeimt/Pao7P+mPp5JyXDhBe5YvOZMYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T16:16:04.215828Z","bundle_sha256":"5f141f088eeb694a9aa072b166283fec725f9bfa85a8a6d034b2d291a33eedb9"}}