{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FOE2SUE2QJ4V4OPEY7HJOA3YSY","short_pith_number":"pith:FOE2SUE2","canonical_record":{"source":{"id":"2502.10431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T12:58:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b0749f2af82ee7793a6bc03e88fc1ddab491833890b7fb1769a4503dce1c7db","abstract_canon_sha256":"1198b775d9c18a9623128bef53464ffa3d29b6ee02d9bb09ce8bff6e3e4d1ad1"},"schema_version":"1.0"},"canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","source":{"kind":"arxiv","id":"2502.10431","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10431","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10431v1","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10431","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"FOE2SUE2QJ4V","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_16","alias_value":"FOE2SUE2QJ4V4OPE","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_8","alias_value":"FOE2SUE2","created_at":"2026-07-05T10:14:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FOE2SUE2QJ4V4OPEY7HJOA3YSY","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T12:58:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b0749f2af82ee7793a6bc03e88fc1ddab491833890b7fb1769a4503dce1c7db","abstract_canon_sha256":"1198b775d9c18a9623128bef53464ffa3d29b6ee02d9bb09ce8bff6e3e4d1ad1"},"schema_version":"1.0"},"canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:52.504898Z","signature_b64":"cRGWVgqUqft2k5eR2JWI4lkRo97XD8xlYCmxVTj4krTKM4TY8nnGWxMAgY4CHR/RqccmXu5o1zs4aOxNXDuzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","last_reissued_at":"2026-07-05T10:14:52.504405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:52.504405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10431","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":"2026-07-05T10:14:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GiNq0bo7AKk9goFLe2mi/XJySe9juGFvQkjQNIuCjnp1efTCgpgP5D8yrZV+tCU18z8s/Yg9lKtcICp63gTQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:25:13.618918Z"},"content_sha256":"0aa3fc6ac853d3d8e05b530e2ee88621bb630108765a7fb2a61a2c440325c96f","schema_version":"1.0","event_id":"sha256:0aa3fc6ac853d3d8e05b530e2ee88621bb630108765a7fb2a61a2c440325c96f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FOE2SUE2QJ4V4OPEY7HJOA3YSY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Constraint Violation Signals For Action-Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Kumar, Janaka Chathuranga Brahmanage, Jiajing Ling","submitted_at":"2025-02-08T12:58:26Z","abstract_excerpt":"In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10431","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/2502.10431/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":"2026-07-05T10:14:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gVuko/U84nZp8V4Jnld4xbeo23Mz1gEBrNmgLvI27iCsHiUGrU7kZoFNTZk3RvM5OTZQt+KPR04lYZUh20HAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:25:13.619788Z"},"content_sha256":"d220da7313537902562a07e0086350bd7cc862f8675705e42435786f81baa4d2","schema_version":"1.0","event_id":"sha256:d220da7313537902562a07e0086350bd7cc862f8675705e42435786f81baa4d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/bundle.json","state_url":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/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":"2026-08-12T04:25:13Z","links":{"resolver":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY","bundle":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/bundle.json","state":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FOE2SUE2QJ4V4OPEY7HJOA3YSY","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":"1198b775d9c18a9623128bef53464ffa3d29b6ee02d9bb09ce8bff6e3e4d1ad1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T12:58:26Z","title_canon_sha256":"7b0749f2af82ee7793a6bc03e88fc1ddab491833890b7fb1769a4503dce1c7db"},"schema_version":"1.0","source":{"id":"2502.10431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10431","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10431v1","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10431","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"FOE2SUE2QJ4V","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_16","alias_value":"FOE2SUE2QJ4V4OPE","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_8","alias_value":"FOE2SUE2","created_at":"2026-07-05T10:14:52Z"}],"graph_snapshots":[{"event_id":"sha256:d220da7313537902562a07e0086350bd7cc862f8675705e42435786f81baa4d2","target":"graph","created_at":"2026-07-05T10:14:52Z","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/2502.10431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using","authors_text":"Akshat Kumar, Janaka Chathuranga Brahmanage, Jiajing Ling","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T12:58:26Z","title":"Leveraging Constraint Violation Signals For Action-Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10431","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":"sha256:0aa3fc6ac853d3d8e05b530e2ee88621bb630108765a7fb2a61a2c440325c96f","target":"record","created_at":"2026-07-05T10:14:52Z","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":"1198b775d9c18a9623128bef53464ffa3d29b6ee02d9bb09ce8bff6e3e4d1ad1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T12:58:26Z","title_canon_sha256":"7b0749f2af82ee7793a6bc03e88fc1ddab491833890b7fb1769a4503dce1c7db"},"schema_version":"1.0","source":{"id":"2502.10431","kind":"arxiv","version":1}},"canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","first_computed_at":"2026-07-05T10:14:52.504405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:52.504405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cRGWVgqUqft2k5eR2JWI4lkRo97XD8xlYCmxVTj4krTKM4TY8nnGWxMAgY4CHR/RqccmXu5o1zs4aOxNXDuzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:52.504898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0aa3fc6ac853d3d8e05b530e2ee88621bb630108765a7fb2a61a2c440325c96f","sha256:d220da7313537902562a07e0086350bd7cc862f8675705e42435786f81baa4d2"],"state_sha256":"b71390994854f76c8f4fb24a5fcd912f89d6ba23c0d65aeb1d8c3f6cc6f93b0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHRMIPHjyP9bDq8ce4J8+Xyq3mAHgrqi+EEeWo9ISwVTNURZdMGNth3C792fug/yYs4Ptv/tIABdVwr0Yo/3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T04:25:13.625236Z","bundle_sha256":"c55a36e8405bfb7f0d888c371aab218963daebee4d4c0c8bdf766a958aef0769"}}