{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:25OCZ5PISW3BQDJGRBA7YDPR2F","short_pith_number":"pith:25OCZ5PI","canonical_record":{"source":{"id":"2111.00886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:22:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"888c193f85914d6d2cb0c87c21b002eeb4b2c7bcf7617d73dd44796deac7ac28","abstract_canon_sha256":"a56b7d007bbbc6f74364cc963fd8168042f483632e28ffa8d87158dac244cd6c"},"schema_version":"1.0"},"canonical_sha256":"d75c2cf5e895b6180d268841fc0df1d17042496907771b54c9d0008179430920","source":{"kind":"arxiv","id":"2111.00886","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00886","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00886v1","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00886","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"25OCZ5PISW3B","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"pith_short_16","alias_value":"25OCZ5PISW3BQDJG","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"pith_short_8","alias_value":"25OCZ5PI","created_at":"2026-07-05T03:27:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:25OCZ5PISW3BQDJGRBA7YDPR2F","target":"record","payload":{"canonical_record":{"source":{"id":"2111.00886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:22:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"888c193f85914d6d2cb0c87c21b002eeb4b2c7bcf7617d73dd44796deac7ac28","abstract_canon_sha256":"a56b7d007bbbc6f74364cc963fd8168042f483632e28ffa8d87158dac244cd6c"},"schema_version":"1.0"},"canonical_sha256":"d75c2cf5e895b6180d268841fc0df1d17042496907771b54c9d0008179430920","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:50.910329Z","signature_b64":"RmLfF/8qKWUJJe83ORGzHU2QCF4qx4Un9AU3mezCKBkIrXx9supjgHfG1Gq4c7zZJ0dwo0bTXYuLlPK8lrKWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75c2cf5e895b6180d268841fc0df1d17042496907771b54c9d0008179430920","last_reissued_at":"2026-07-05T03:27:50.909957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:50.909957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.00886","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":"2026-07-05T03:27:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aix8ttpFIm1Fy/hbmToxEcAHfwy8GppoZBFJgN+Gi27yosmpdDxispMBvI5Y6jmYJx7A0TLl5e/sI2ggJk6qBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:24:39.449004Z"},"content_sha256":"4f6c325d407f30871651ec4f67a0ae15202fd6247446e9b0a8bd3c5065526b91","schema_version":"1.0","event_id":"sha256:4f6c325d407f30871651ec4f67a0ae15202fd6247446e9b0a8bd3c5065526b91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:25OCZ5PISW3BQDJGRBA7YDPR2F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intervention Efficient Algorithm for Two-Stage Causal MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aurghya Maiti, Gaurav Sinha, Rahul Madhavan, Siddharth Barman","submitted_at":"2021-11-01T12:22:37Z","abstract_excerpt":"We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on variables at each state. Generalizing the recent causal-bandit framework, the current work develops (simple) regret minimization guarantees for two-stage causal MDPs, with parallel causal graph at each state. We propose an algorithm that achieves an instance dependent regret bound. A key feature of our algorithm is that it utilizes convex optimization to address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00886","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/2111.00886/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":"2026-07-05T03:27:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBNp/rRLHeQt3pQzKY4PP0nHWOEHw/4hIv4srIrRRl5R0eIpNVuVeIX9NsdGSFzAgJ5e//hgk2iHN0K6KNY6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:24:39.449385Z"},"content_sha256":"79ba91f049e4bd5abb49b7f7f30918db61aa25fac0bcd192f7cf236830f7f83d","schema_version":"1.0","event_id":"sha256:79ba91f049e4bd5abb49b7f7f30918db61aa25fac0bcd192f7cf236830f7f83d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25OCZ5PISW3BQDJGRBA7YDPR2F/bundle.json","state_url":"https://pith.science/pith/25OCZ5PISW3BQDJGRBA7YDPR2F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25OCZ5PISW3BQDJGRBA7YDPR2F/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":"2026-07-06T20:24:39Z","links":{"resolver":"https://pith.science/pith/25OCZ5PISW3BQDJGRBA7YDPR2F","bundle":"https://pith.science/pith/25OCZ5PISW3BQDJGRBA7YDPR2F/bundle.json","state":"https://pith.science/pith/25OCZ5PISW3BQDJGRBA7YDPR2F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25OCZ5PISW3BQDJGRBA7YDPR2F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:25OCZ5PISW3BQDJGRBA7YDPR2F","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":"a56b7d007bbbc6f74364cc963fd8168042f483632e28ffa8d87158dac244cd6c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:22:37Z","title_canon_sha256":"888c193f85914d6d2cb0c87c21b002eeb4b2c7bcf7617d73dd44796deac7ac28"},"schema_version":"1.0","source":{"id":"2111.00886","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00886","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00886v1","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00886","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"pith_short_12","alias_value":"25OCZ5PISW3B","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"pith_short_16","alias_value":"25OCZ5PISW3BQDJG","created_at":"2026-07-05T03:27:50Z"},{"alias_kind":"pith_short_8","alias_value":"25OCZ5PI","created_at":"2026-07-05T03:27:50Z"}],"graph_snapshots":[{"event_id":"sha256:79ba91f049e4bd5abb49b7f7f30918db61aa25fac0bcd192f7cf236830f7f83d","target":"graph","created_at":"2026-07-05T03:27:50Z","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/2111.00886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on variables at each state. Generalizing the recent causal-bandit framework, the current work develops (simple) regret minimization guarantees for two-stage causal MDPs, with parallel causal graph at each state. We propose an algorithm that achieves an instance dependent regret bound. A key feature of our algorithm is that it utilizes convex optimization to address","authors_text":"Aurghya Maiti, Gaurav Sinha, Rahul Madhavan, Siddharth Barman","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:22:37Z","title":"Intervention Efficient Algorithm for Two-Stage Causal MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00886","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":"sha256:4f6c325d407f30871651ec4f67a0ae15202fd6247446e9b0a8bd3c5065526b91","target":"record","created_at":"2026-07-05T03:27:50Z","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":"a56b7d007bbbc6f74364cc963fd8168042f483632e28ffa8d87158dac244cd6c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:22:37Z","title_canon_sha256":"888c193f85914d6d2cb0c87c21b002eeb4b2c7bcf7617d73dd44796deac7ac28"},"schema_version":"1.0","source":{"id":"2111.00886","kind":"arxiv","version":1}},"canonical_sha256":"d75c2cf5e895b6180d268841fc0df1d17042496907771b54c9d0008179430920","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d75c2cf5e895b6180d268841fc0df1d17042496907771b54c9d0008179430920","first_computed_at":"2026-07-05T03:27:50.909957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:50.909957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RmLfF/8qKWUJJe83ORGzHU2QCF4qx4Un9AU3mezCKBkIrXx9supjgHfG1Gq4c7zZJ0dwo0bTXYuLlPK8lrKWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:50.910329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00886","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f6c325d407f30871651ec4f67a0ae15202fd6247446e9b0a8bd3c5065526b91","sha256:79ba91f049e4bd5abb49b7f7f30918db61aa25fac0bcd192f7cf236830f7f83d"],"state_sha256":"844c0d4eac55ac9ec08de857cafeaebab14696e09c07c8dff2765c61322af55d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZPc7yCQSirnRdPxfG5reIZlkKTLsgX22yAqsc6H2dOknlzASv7Ls6Ex/DFVf38iTzBsZ5gbknnRXM+cyKEZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:24:39.451240Z","bundle_sha256":"f2eac3c40fac20ce293b506dac215d20bf184c05126a1b34b56f1eebc05b02ac"}}