{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MYRJRNDW6QQTNVPSOTVZ2TU2HL","short_pith_number":"pith:MYRJRNDW","canonical_record":{"source":{"id":"1910.13393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-29T16:56:21Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"654d67cc39cb3eb86c216cf71517eced78bd20e0bdfbc774352f454de878b78d","abstract_canon_sha256":"38b07975e241e4fd893491d7893b336d49fa3345e591e479411d484d63767450"},"schema_version":"1.0"},"canonical_sha256":"662298b476f42136d5f274eb9d4e9a3afa105f10c2ee23839c98f6c3d6e3a401","source":{"kind":"arxiv","id":"1910.13393","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.13393","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"1910.13393v1","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13393","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"MYRJRNDW6QQT","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"MYRJRNDW6QQTNVPS","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"MYRJRNDW","created_at":"2026-07-05T00:15:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MYRJRNDW6QQTNVPSOTVZ2TU2HL","target":"record","payload":{"canonical_record":{"source":{"id":"1910.13393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-29T16:56:21Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"654d67cc39cb3eb86c216cf71517eced78bd20e0bdfbc774352f454de878b78d","abstract_canon_sha256":"38b07975e241e4fd893491d7893b336d49fa3345e591e479411d484d63767450"},"schema_version":"1.0"},"canonical_sha256":"662298b476f42136d5f274eb9d4e9a3afa105f10c2ee23839c98f6c3d6e3a401","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:44.279422Z","signature_b64":"QUrDdNMu1sFS26ADQbJzPKQUWtacNwQdZJbC25jeL5PTiPaYCmXA4MAGvj7hLG/cwX4MKBtpAnjVEy/dof48BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"662298b476f42136d5f274eb9d4e9a3afa105f10c2ee23839c98f6c3d6e3a401","last_reissued_at":"2026-07-05T00:15:44.278908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:44.278908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.13393","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":"2026-07-05T00:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkR0qMrTQGcjaNp78CH0I5Ok3kJVhbfva7QhLR/6s1l9nWRTMGvrD/6aPFw1jliTyQ7chxu52J86hO2lHalbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:49:34.357694Z"},"content_sha256":"eb90f420f89c790bea556d0bba30dc228bdbfceaa0caaf390d6f6b4117855bb8","schema_version":"1.0","event_id":"sha256:eb90f420f89c790bea556d0bba30dc228bdbfceaa0caaf390d6f6b4117855bb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MYRJRNDW6QQTNVPSOTVZ2TU2HL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Reinforcement Learning Has Zero Duality Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Luiz F.O. Chamon, Miguel Calvo-Fullana, Santiago Paternain","submitted_at":"2019-10-29T16:56:21Z","abstract_excerpt":"Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple opponents. In the context of reinforcement learning~(RL), these problems are addressed by (i)~designing a reward function that simultaneously describes all requirements or (ii)~combining modular value functions that encode them individually. Though effective, these methods have critical downsides. Designing good reward functions that balance different objectives is challenging, especially as the number of objectives g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13393","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/1910.13393/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":"2026-07-05T00:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DejmTxjhI39fUyr0wCwmMw+cG6BGKSxM19JxJl/35Xgk4fZvIOKb7X3/ZEH5rmqOTN6q5gHfegHzvktGmDAPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:49:34.358276Z"},"content_sha256":"4917721615ff41d8f7ac4cde1be29d435573b7e4fd5a4282d00913688d719a45","schema_version":"1.0","event_id":"sha256:4917721615ff41d8f7ac4cde1be29d435573b7e4fd5a4282d00913688d719a45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL/bundle.json","state_url":"https://pith.science/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL/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":"2026-08-12T17:49:34Z","links":{"resolver":"https://pith.science/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL","bundle":"https://pith.science/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL/bundle.json","state":"https://pith.science/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYRJRNDW6QQTNVPSOTVZ2TU2HL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MYRJRNDW6QQTNVPSOTVZ2TU2HL","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":"38b07975e241e4fd893491d7893b336d49fa3345e591e479411d484d63767450","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-29T16:56:21Z","title_canon_sha256":"654d67cc39cb3eb86c216cf71517eced78bd20e0bdfbc774352f454de878b78d"},"schema_version":"1.0","source":{"id":"1910.13393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.13393","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"1910.13393v1","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13393","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"MYRJRNDW6QQT","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"MYRJRNDW6QQTNVPS","created_at":"2026-07-05T00:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"MYRJRNDW","created_at":"2026-07-05T00:15:44Z"}],"graph_snapshots":[{"event_id":"sha256:4917721615ff41d8f7ac4cde1be29d435573b7e4fd5a4282d00913688d719a45","target":"graph","created_at":"2026-07-05T00:15:44Z","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/1910.13393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple opponents. In the context of reinforcement learning~(RL), these problems are addressed by (i)~designing a reward function that simultaneously describes all requirements or (ii)~combining modular value functions that encode them individually. Though effective, these methods have critical downsides. Designing good reward functions that balance different objectives is challenging, especially as the number of objectives g","authors_text":"Alejandro Ribeiro, Luiz F.O. Chamon, Miguel Calvo-Fullana, Santiago Paternain","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-29T16:56:21Z","title":"Constrained Reinforcement Learning Has Zero Duality Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13393","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:eb90f420f89c790bea556d0bba30dc228bdbfceaa0caaf390d6f6b4117855bb8","target":"record","created_at":"2026-07-05T00:15:44Z","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":"38b07975e241e4fd893491d7893b336d49fa3345e591e479411d484d63767450","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-29T16:56:21Z","title_canon_sha256":"654d67cc39cb3eb86c216cf71517eced78bd20e0bdfbc774352f454de878b78d"},"schema_version":"1.0","source":{"id":"1910.13393","kind":"arxiv","version":1}},"canonical_sha256":"662298b476f42136d5f274eb9d4e9a3afa105f10c2ee23839c98f6c3d6e3a401","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"662298b476f42136d5f274eb9d4e9a3afa105f10c2ee23839c98f6c3d6e3a401","first_computed_at":"2026-07-05T00:15:44.278908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:15:44.278908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QUrDdNMu1sFS26ADQbJzPKQUWtacNwQdZJbC25jeL5PTiPaYCmXA4MAGvj7hLG/cwX4MKBtpAnjVEy/dof48BA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:15:44.279422Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.13393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb90f420f89c790bea556d0bba30dc228bdbfceaa0caaf390d6f6b4117855bb8","sha256:4917721615ff41d8f7ac4cde1be29d435573b7e4fd5a4282d00913688d719a45"],"state_sha256":"ed7b5e0697b787d1d6ecf29c7e6926cc4d04f84d36eb0026065584f5e772e10e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lc6eW+xAuoxEQeQm/Nes+h4QcNIwKw/YxuktWH20UyWtRgDw1bxOzNkmcWaNxXmadhHWhRFc/zoen7j2zkR2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T17:49:34.362654Z","bundle_sha256":"326adee718c5666dd5d4cb21004d75608ea6b1dba52f18d63020178873e369ca"}}