{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BY357CDVIBBNZHEUYJTJPDU5R4","short_pith_number":"pith:BY357CDV","canonical_record":{"source":{"id":"2301.10339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T22:51:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b2541b498ed962a0d11d0c6aecdf8160f8a6b7bcec4d14e405e1415baa1e2224","abstract_canon_sha256":"5008339d63264c0a137fc3f315c1fc1f1792d08dcfa16623c6f37594807cd84b"},"schema_version":"1.0"},"canonical_sha256":"0e37df88754042dc9c94c266978e9d8f094d2a5cced497c301304cc468137435","source":{"kind":"arxiv","id":"2301.10339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10339","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10339v1","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10339","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"pith_short_12","alias_value":"BY357CDVIBBN","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"pith_short_16","alias_value":"BY357CDVIBBNZHEU","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"pith_short_8","alias_value":"BY357CDV","created_at":"2026-07-05T05:35:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BY357CDVIBBNZHEUYJTJPDU5R4","target":"record","payload":{"canonical_record":{"source":{"id":"2301.10339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T22:51:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b2541b498ed962a0d11d0c6aecdf8160f8a6b7bcec4d14e405e1415baa1e2224","abstract_canon_sha256":"5008339d63264c0a137fc3f315c1fc1f1792d08dcfa16623c6f37594807cd84b"},"schema_version":"1.0"},"canonical_sha256":"0e37df88754042dc9c94c266978e9d8f094d2a5cced497c301304cc468137435","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:50.107076Z","signature_b64":"DJosHE94dZz1WOYyr8eZieHGWKZLLTZT5vCb6auMaRsWPV454xS8EglCiOwb5y+nLClWSaFv8Fh05QiNk6DQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e37df88754042dc9c94c266978e9d8f094d2a5cced497c301304cc468137435","last_reissued_at":"2026-07-05T05:35:50.106529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:50.106529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.10339","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":"2026-07-05T05:35:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uzlgVEPIn4Jpt9IfBRRZfG1y53VsdeUrxyZ9r+NfADkyNVHfPHNJmSZ6/gVRzOobnPAWKl0Mzwn5HElwDO9hAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T07:33:47.193072Z"},"content_sha256":"0eb3b8cd1d5b9eb7972912d592274c9f8a3c8d0ebed1d81c448b48d1461684b5","schema_version":"1.0","event_id":"sha256:0eb3b8cd1d5b9eb7972912d592274c9f8a3c8d0ebed1d81c448b48d1461684b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BY357CDVIBBNZHEUYJTJPDU5R4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Tairan He, Weiye Zhao","submitted_at":"2023-01-24T22:51:29Z","abstract_excerpt":"Safety is a critical hurdle that limits the application of deep reinforcement learning (RL) to real-world control tasks. To this end, constrained reinforcement learning leverages cost functions to improve safety in constrained Markov decision processes. However, such constrained RL methods fail to achieve zero violation even when the cost limit is zero. This paper analyzes the reason for such failure, which suggests that a proper cost function plays an important role in constrained RL. Inspired by the analysis, we propose AutoCost, a simple yet effective framework that automatically searches f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10339","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/2301.10339/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":"2026-07-05T05:35:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+/dy6gqH+vkIJRkr/CwJJlI8UZpv8VjfVZbxSql7Y/myjGNKL5zQ92W1Zy3pe/CcNv0WLlkwOjb/tArQ8SRVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T07:33:47.193467Z"},"content_sha256":"746a01dd7cf6ae9fe0f24d96a36b14cf14a09c0b581c81acab613c6bf7f041a4","schema_version":"1.0","event_id":"sha256:746a01dd7cf6ae9fe0f24d96a36b14cf14a09c0b581c81acab613c6bf7f041a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BY357CDVIBBNZHEUYJTJPDU5R4/bundle.json","state_url":"https://pith.science/pith/BY357CDVIBBNZHEUYJTJPDU5R4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BY357CDVIBBNZHEUYJTJPDU5R4/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":"2026-07-13T07:33:47Z","links":{"resolver":"https://pith.science/pith/BY357CDVIBBNZHEUYJTJPDU5R4","bundle":"https://pith.science/pith/BY357CDVIBBNZHEUYJTJPDU5R4/bundle.json","state":"https://pith.science/pith/BY357CDVIBBNZHEUYJTJPDU5R4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BY357CDVIBBNZHEUYJTJPDU5R4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BY357CDVIBBNZHEUYJTJPDU5R4","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":"5008339d63264c0a137fc3f315c1fc1f1792d08dcfa16623c6f37594807cd84b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T22:51:29Z","title_canon_sha256":"b2541b498ed962a0d11d0c6aecdf8160f8a6b7bcec4d14e405e1415baa1e2224"},"schema_version":"1.0","source":{"id":"2301.10339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10339","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10339v1","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10339","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"pith_short_12","alias_value":"BY357CDVIBBN","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"pith_short_16","alias_value":"BY357CDVIBBNZHEU","created_at":"2026-07-05T05:35:50Z"},{"alias_kind":"pith_short_8","alias_value":"BY357CDV","created_at":"2026-07-05T05:35:50Z"}],"graph_snapshots":[{"event_id":"sha256:746a01dd7cf6ae9fe0f24d96a36b14cf14a09c0b581c81acab613c6bf7f041a4","target":"graph","created_at":"2026-07-05T05:35:50Z","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/2301.10339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety is a critical hurdle that limits the application of deep reinforcement learning (RL) to real-world control tasks. To this end, constrained reinforcement learning leverages cost functions to improve safety in constrained Markov decision processes. However, such constrained RL methods fail to achieve zero violation even when the cost limit is zero. This paper analyzes the reason for such failure, which suggests that a proper cost function plays an important role in constrained RL. Inspired by the analysis, we propose AutoCost, a simple yet effective framework that automatically searches f","authors_text":"Changliu Liu, Tairan He, Weiye Zhao","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T22:51:29Z","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10339","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":"sha256:0eb3b8cd1d5b9eb7972912d592274c9f8a3c8d0ebed1d81c448b48d1461684b5","target":"record","created_at":"2026-07-05T05:35:50Z","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":"5008339d63264c0a137fc3f315c1fc1f1792d08dcfa16623c6f37594807cd84b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T22:51:29Z","title_canon_sha256":"b2541b498ed962a0d11d0c6aecdf8160f8a6b7bcec4d14e405e1415baa1e2224"},"schema_version":"1.0","source":{"id":"2301.10339","kind":"arxiv","version":1}},"canonical_sha256":"0e37df88754042dc9c94c266978e9d8f094d2a5cced497c301304cc468137435","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e37df88754042dc9c94c266978e9d8f094d2a5cced497c301304cc468137435","first_computed_at":"2026-07-05T05:35:50.106529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:35:50.106529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DJosHE94dZz1WOYyr8eZieHGWKZLLTZT5vCb6auMaRsWPV454xS8EglCiOwb5y+nLClWSaFv8Fh05QiNk6DQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:35:50.107076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.10339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eb3b8cd1d5b9eb7972912d592274c9f8a3c8d0ebed1d81c448b48d1461684b5","sha256:746a01dd7cf6ae9fe0f24d96a36b14cf14a09c0b581c81acab613c6bf7f041a4"],"state_sha256":"0ebd1c9034b1454ba07f0d085770b9084b4cc9fdb4e2ba405fc0f7c05ee61200"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxeXqiiCt7fYoWvilJVYrcIkoZGOFvnxnomfJJDCZoY6dlU1YpzOu4RzpkIaiVLKe/9vP3AcM2z/GREuZR7GBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T07:33:47.195619Z","bundle_sha256":"97c6065c06102f8f784cd54698d203a66b3d3b793f44c9846c70b42911500a19"}}