{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7LLK7SN3VLGOQQKDZJVXJIIWFW","short_pith_number":"pith:7LLK7SN3","canonical_record":{"source":{"id":"2007.03964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-07-08T08:43:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"059f65172511c0b777348b4a2ddc961be3535c4b3b11aea022be812b1e4fdabe","abstract_canon_sha256":"6f5e17daf9bdff361bdfed797a1909621102ab8cccff6b887cf05afb87440f3e"},"schema_version":"1.0"},"canonical_sha256":"fad6afc9bbaacce84143ca6b74a1162db3871630b197def040b2124fe0faf437","source":{"kind":"arxiv","id":"2007.03964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03964","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03964v1","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03964","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"7LLK7SN3VLGO","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"pith_short_16","alias_value":"7LLK7SN3VLGOQQKD","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"pith_short_8","alias_value":"7LLK7SN3","created_at":"2026-07-05T01:17:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7LLK7SN3VLGOQQKDZJVXJIIWFW","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-07-08T08:43:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"059f65172511c0b777348b4a2ddc961be3535c4b3b11aea022be812b1e4fdabe","abstract_canon_sha256":"6f5e17daf9bdff361bdfed797a1909621102ab8cccff6b887cf05afb87440f3e"},"schema_version":"1.0"},"canonical_sha256":"fad6afc9bbaacce84143ca6b74a1162db3871630b197def040b2124fe0faf437","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:10.791749Z","signature_b64":"RO25pYup/RlqZwtFtN1QN73VwrambVKU9kiSMIKCwaIi5Yv1G5YQ/etT6/XfENL1hrsIe1I++Jk04dtnxC0gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fad6afc9bbaacce84143ca6b74a1162db3871630b197def040b2124fe0faf437","last_reissued_at":"2026-07-05T01:17:10.791288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:10.791288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03964","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":"2026-07-05T01:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S9lpMXSuih7uq2bL+diQciIZNJM2zPhBCjdagcJJWpSUbXLqwpzIRp73I4hbXWIxYnSMSKYUJI/QS0BPJEuvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:10:23.435861Z"},"content_sha256":"fdf44e805627967d5fadb47ddb0ec21358316c9a9a34de21073e2bf1fdf4623d","schema_version":"1.0","event_id":"sha256:fdf44e805627967d5fadb47ddb0ec21358316c9a9a34de21073e2bf1fdf4623d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7LLK7SN3VLGOQQKDZJVXJIIWFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"math.OC","authors_text":"Adam Stooke, Joshua Achiam, Pieter Abbeel","submitted_at":"2020-07-08T08:43:14Z","abstract_excerpt":"Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior during agent training. We address this shortcoming by proposing a novel Lagrange multiplier update method that utilizes derivatives of the constraint function. We take a controls perspective, wherein the traditional Lagrange multiplier update behaves as \\emph{integral} control; our terms introduce \\emph{proportional} and \\emph{derivative} control, achieving f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03964","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/2007.03964/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":"2026-07-05T01:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3E9Gwen4UAc8BM5cWAj+CG3RgXsG0BhfRTTQRMT2W8ZZMAJbTMR9rAkK4Ah0EeDmIXCCdaJMkrEdKt2L2mRzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:10:23.436928Z"},"content_sha256":"af303d81c632f705d6ebe65e952da80be9ab79caa2b69f74f19c8d3bc657450d","schema_version":"1.0","event_id":"sha256:af303d81c632f705d6ebe65e952da80be9ab79caa2b69f74f19c8d3bc657450d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW/bundle.json","state_url":"https://pith.science/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW/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":"2026-08-08T01:10:23Z","links":{"resolver":"https://pith.science/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW","bundle":"https://pith.science/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW/bundle.json","state":"https://pith.science/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7LLK7SN3VLGOQQKDZJVXJIIWFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7LLK7SN3VLGOQQKDZJVXJIIWFW","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":"6f5e17daf9bdff361bdfed797a1909621102ab8cccff6b887cf05afb87440f3e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-07-08T08:43:14Z","title_canon_sha256":"059f65172511c0b777348b4a2ddc961be3535c4b3b11aea022be812b1e4fdabe"},"schema_version":"1.0","source":{"id":"2007.03964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03964","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03964v1","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03964","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"7LLK7SN3VLGO","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"pith_short_16","alias_value":"7LLK7SN3VLGOQQKD","created_at":"2026-07-05T01:17:10Z"},{"alias_kind":"pith_short_8","alias_value":"7LLK7SN3","created_at":"2026-07-05T01:17:10Z"}],"graph_snapshots":[{"event_id":"sha256:af303d81c632f705d6ebe65e952da80be9ab79caa2b69f74f19c8d3bc657450d","target":"graph","created_at":"2026-07-05T01:17:10Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.03964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior during agent training. We address this shortcoming by proposing a novel Lagrange multiplier update method that utilizes derivatives of the constraint function. We take a controls perspective, wherein the traditional Lagrange multiplier update behaves as \\emph{integral} control; our terms introduce \\emph{proportional} and \\emph{derivative} control, achieving f","authors_text":"Adam Stooke, Joshua Achiam, Pieter Abbeel","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-07-08T08:43:14Z","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03964","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:fdf44e805627967d5fadb47ddb0ec21358316c9a9a34de21073e2bf1fdf4623d","target":"record","created_at":"2026-07-05T01:17:10Z","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":"6f5e17daf9bdff361bdfed797a1909621102ab8cccff6b887cf05afb87440f3e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-07-08T08:43:14Z","title_canon_sha256":"059f65172511c0b777348b4a2ddc961be3535c4b3b11aea022be812b1e4fdabe"},"schema_version":"1.0","source":{"id":"2007.03964","kind":"arxiv","version":1}},"canonical_sha256":"fad6afc9bbaacce84143ca6b74a1162db3871630b197def040b2124fe0faf437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fad6afc9bbaacce84143ca6b74a1162db3871630b197def040b2124fe0faf437","first_computed_at":"2026-07-05T01:17:10.791288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:10.791288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RO25pYup/RlqZwtFtN1QN73VwrambVKU9kiSMIKCwaIi5Yv1G5YQ/etT6/XfENL1hrsIe1I++Jk04dtnxC0gDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:10.791749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdf44e805627967d5fadb47ddb0ec21358316c9a9a34de21073e2bf1fdf4623d","sha256:af303d81c632f705d6ebe65e952da80be9ab79caa2b69f74f19c8d3bc657450d"],"state_sha256":"59fa70b42d86507eefa1f50d864623dfd61a21d92f4cf47dc972d1ef6bbb568c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nns5zr9z9G6eIFQ+GtVMt4NfJa656e07S+ax3KD1MmXAQ1bFEz6TGdNDps2VF8jCsoxkayjVRV3xUJkuKjaUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:10:23.444094Z","bundle_sha256":"832ae99ad1d9b3f4e598c779bd780ab3df764a98fa376d33f9c298009c01c905"}}