{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FJ2I75DATDQIBJ6FLH7RCWCXTX","short_pith_number":"pith:FJ2I75DA","canonical_record":{"source":{"id":"2601.21845","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:21:37Z","cross_cats_sorted":[],"title_canon_sha256":"7526daba35c70a51234d9b2a1af712f3f2d81c5bdce968c54cb63d52a600083a","abstract_canon_sha256":"37d0ca0724c5a9eccfa0df30ba01b50d3e3b8f1f69b6eb821ba1851023fbfa27"},"schema_version":"1.0"},"canonical_sha256":"2a748ff46098e080a7c559ff1158579dc57da3a1d6982344129a45488cd28c3e","source":{"kind":"arxiv","id":"2601.21845","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21845","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21845v2","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21845","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"FJ2I75DATDQI","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"FJ2I75DATDQIBJ6F","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"FJ2I75DA","created_at":"2026-05-27T01:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FJ2I75DATDQIBJ6FLH7RCWCXTX","target":"record","payload":{"canonical_record":{"source":{"id":"2601.21845","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:21:37Z","cross_cats_sorted":[],"title_canon_sha256":"7526daba35c70a51234d9b2a1af712f3f2d81c5bdce968c54cb63d52a600083a","abstract_canon_sha256":"37d0ca0724c5a9eccfa0df30ba01b50d3e3b8f1f69b6eb821ba1851023fbfa27"},"schema_version":"1.0"},"canonical_sha256":"2a748ff46098e080a7c559ff1158579dc57da3a1d6982344129a45488cd28c3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:43.309661Z","signature_b64":"INZaTQRheTRu89ZerR1f2Do6EBl11y2/rLN3ZL+p6dUoP5PgJRmGo1NBj4I6fHwnTfJVJVRF72Q6wIzBGQtEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a748ff46098e080a7c559ff1158579dc57da3a1d6982344129a45488cd28c3e","last_reissued_at":"2026-05-27T01:05:43.306146Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:43.306146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.21845","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t17ldL8p62Soao8VtvMqX9bAaBoP/PwYY4AidQAmFS4j5v8BGxJcd2BSczgOeSHm+JjUIsSoQhNYaHM92LbCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:24:48.559058Z"},"content_sha256":"e2dc92d00e333c56bb473135f4995c89c98bfccab186ba521f7e8133b23534d2","schema_version":"1.0","event_id":"sha256:e2dc92d00e333c56bb473135f4995c89c98bfccab186ba521f7e8133b23534d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FJ2I75DATDQIBJ6FLH7RCWCXTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Meta Reinforcement Learning with Provable Test-Time Safety","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Maryam Kamgarpour, Tingting Ni","submitted_at":"2026-01-29T15:21:37Z","abstract_excerpt":"Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving sample complexity on test tasks, many real-world applications, such as robotics and healthcare, impose safety constraints during testing. Constrained meta RL provides a promising framework for integrating safety into meta RL. An open question in constrained meta RL is how to ensure safety of the policy on the real-world test task, while reducing the sample compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21845","kind":"arxiv","version":2},"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/2601.21845/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":"2026-05-27T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L0kz4eWz5tPLj0E5HphGjVVjq1gxxvksAjmD1cwH8ivzaGg9dQR4SqA4xWGdV+zLespKJvwggb0nzZf+UGiAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:24:48.559749Z"},"content_sha256":"1200b9e45432af3201864e42e93b845fca2b31299d003b8daa4b47eb65896b36","schema_version":"1.0","event_id":"sha256:1200b9e45432af3201864e42e93b845fca2b31299d003b8daa4b47eb65896b36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX/bundle.json","state_url":"https://pith.science/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX/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":"2026-05-27T19:24:48Z","links":{"resolver":"https://pith.science/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX","bundle":"https://pith.science/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX/bundle.json","state":"https://pith.science/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJ2I75DATDQIBJ6FLH7RCWCXTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FJ2I75DATDQIBJ6FLH7RCWCXTX","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":"37d0ca0724c5a9eccfa0df30ba01b50d3e3b8f1f69b6eb821ba1851023fbfa27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:21:37Z","title_canon_sha256":"7526daba35c70a51234d9b2a1af712f3f2d81c5bdce968c54cb63d52a600083a"},"schema_version":"1.0","source":{"id":"2601.21845","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21845","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21845v2","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21845","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"FJ2I75DATDQI","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"FJ2I75DATDQIBJ6F","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"FJ2I75DA","created_at":"2026-05-27T01:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:1200b9e45432af3201864e42e93b845fca2b31299d003b8daa4b47eb65896b36","target":"graph","created_at":"2026-05-27T01:05:43Z","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/2601.21845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving sample complexity on test tasks, many real-world applications, such as robotics and healthcare, impose safety constraints during testing. Constrained meta RL provides a promising framework for integrating safety into meta RL. An open question in constrained meta RL is how to ensure safety of the policy on the real-world test task, while reducing the sample compl","authors_text":"Maryam Kamgarpour, Tingting Ni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:21:37Z","title":"Constrained Meta Reinforcement Learning with Provable Test-Time Safety"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21845","kind":"arxiv","version":2},"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:e2dc92d00e333c56bb473135f4995c89c98bfccab186ba521f7e8133b23534d2","target":"record","created_at":"2026-05-27T01:05:43Z","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":"37d0ca0724c5a9eccfa0df30ba01b50d3e3b8f1f69b6eb821ba1851023fbfa27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T15:21:37Z","title_canon_sha256":"7526daba35c70a51234d9b2a1af712f3f2d81c5bdce968c54cb63d52a600083a"},"schema_version":"1.0","source":{"id":"2601.21845","kind":"arxiv","version":2}},"canonical_sha256":"2a748ff46098e080a7c559ff1158579dc57da3a1d6982344129a45488cd28c3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a748ff46098e080a7c559ff1158579dc57da3a1d6982344129a45488cd28c3e","first_computed_at":"2026-05-27T01:05:43.306146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:43.306146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"INZaTQRheTRu89ZerR1f2Do6EBl11y2/rLN3ZL+p6dUoP5PgJRmGo1NBj4I6fHwnTfJVJVRF72Q6wIzBGQtEDw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:43.309661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21845","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2dc92d00e333c56bb473135f4995c89c98bfccab186ba521f7e8133b23534d2","sha256:1200b9e45432af3201864e42e93b845fca2b31299d003b8daa4b47eb65896b36"],"state_sha256":"f407e6d2b5521e9c55c219081f3cb57775885e3a0d5cd02133455005eed59c1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNKsZ8zuQb3ghiNFSiOU3AeotV3Yexl+jN75IHg1Lh4JsSjpIAvjc022amUolyzdKHfzIpX/UU4/M5F78GuTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:24:48.563136Z","bundle_sha256":"cbd04ccba660c3c37dd4abb847a2588277f793c0e3e0294c4320e64b71a1c90b"}}