{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CQQASSKLIKG4LZFHGZUTP753NA","short_pith_number":"pith:CQQASSKL","canonical_record":{"source":{"id":"2403.19462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T14:34:02Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"bb78a8268be84c0887da3c089047e9ee7733ad9be2e58a02bb151ff421aedaa2","abstract_canon_sha256":"1ca6a5b01b2f2ddb3052ac10a6627b8b2ed898d63c614c2d79c0c318a8119cd8"},"schema_version":"1.0"},"canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","source":{"kind":"arxiv","id":"2403.19462","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19462","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19462v1","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19462","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"CQQASSKLIKG4","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"CQQASSKLIKG4LZFH","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"CQQASSKL","created_at":"2026-07-05T08:01:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CQQASSKLIKG4LZFHGZUTP753NA","target":"record","payload":{"canonical_record":{"source":{"id":"2403.19462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T14:34:02Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"bb78a8268be84c0887da3c089047e9ee7733ad9be2e58a02bb151ff421aedaa2","abstract_canon_sha256":"1ca6a5b01b2f2ddb3052ac10a6627b8b2ed898d63c614c2d79c0c318a8119cd8"},"schema_version":"1.0"},"canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:49.238848Z","signature_b64":"N/eHFdoRMKStLa9jR1TqMQIEPw3NdPRJxWXNm+iFc4DP9+79JJOTs79kGnkvYGt+/HraG6nUWEACd8dhr9/XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","last_reissued_at":"2026-07-05T08:01:49.238374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:49.238374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.19462","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":"2026-07-05T08:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3yCe0uVXPcNgwP9veHX3TSQ9s66Mz+aHby22z+LaDCGskOh6XpZ8/ZV2wvbTC2QVveVwMaUV7PG41PKpy9JdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:09:03.542863Z"},"content_sha256":"d0fbc1ea039720fc2b2cc53e5f381b3da45c991821c0b464c633dde47e16021f","schema_version":"1.0","event_id":"sha256:d0fbc1ea039720fc2b2cc53e5f381b3da45c991821c0b464c633dde47e16021f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CQQASSKLIKG4LZFHGZUTP753NA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Mircea Trofin, Teodor V. Marinov","submitted_at":"2024-03-28T14:34:02Z","abstract_excerpt":"This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong performance in complementary parts of the state space. The goal is to learn a policy which performs as well as the best combination of baselines on the entire state space. We propose a simple imitation learning based algorithm, show a sample complexity bound on its accuracy and prove that the the algorithm is minimax optimal by showing a matching lower bound. Further, we apply the alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19462","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/2403.19462/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":"2026-07-05T08:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJjZajklvB4WA487eMvZz0OSkDFY/pcQISKHTNvLhK3PCz3DLIh0KPbK7gzN2batU9lsOANcQ7KRrg0kLMzEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:09:03.543462Z"},"content_sha256":"6d001c1a46104c4dff5d2a78ebdc5ac3a797105387e2e0982000e0f62ea34bba","schema_version":"1.0","event_id":"sha256:6d001c1a46104c4dff5d2a78ebdc5ac3a797105387e2e0982000e0f62ea34bba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/bundle.json","state_url":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQQASSKLIKG4LZFHGZUTP753NA/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":"2026-08-20T08:09:03Z","links":{"resolver":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA","bundle":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/bundle.json","state":"https://pith.science/pith/CQQASSKLIKG4LZFHGZUTP753NA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQQASSKLIKG4LZFHGZUTP753NA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQQASSKLIKG4LZFHGZUTP753NA","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":"1ca6a5b01b2f2ddb3052ac10a6627b8b2ed898d63c614c2d79c0c318a8119cd8","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T14:34:02Z","title_canon_sha256":"bb78a8268be84c0887da3c089047e9ee7733ad9be2e58a02bb151ff421aedaa2"},"schema_version":"1.0","source":{"id":"2403.19462","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19462","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19462v1","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19462","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"CQQASSKLIKG4","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"CQQASSKLIKG4LZFH","created_at":"2026-07-05T08:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"CQQASSKL","created_at":"2026-07-05T08:01:49Z"}],"graph_snapshots":[{"event_id":"sha256:6d001c1a46104c4dff5d2a78ebdc5ac3a797105387e2e0982000e0f62ea34bba","target":"graph","created_at":"2026-07-05T08:01:49Z","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/2403.19462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work studies a Reinforcement Learning (RL) problem in which we are given a set of trajectories collected with K baseline policies. Each of these policies can be quite suboptimal in isolation, and have strong performance in complementary parts of the state space. The goal is to learn a policy which performs as well as the best combination of baselines on the entire state space. We propose a simple imitation learning based algorithm, show a sample complexity bound on its accuracy and prove that the the algorithm is minimax optimal by showing a matching lower bound. Further, we apply the alg","authors_text":"Alekh Agarwal, Mircea Trofin, Teodor V. Marinov","cross_cats":["cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T14:34:02Z","title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19462","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:d0fbc1ea039720fc2b2cc53e5f381b3da45c991821c0b464c633dde47e16021f","target":"record","created_at":"2026-07-05T08:01:49Z","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":"1ca6a5b01b2f2ddb3052ac10a6627b8b2ed898d63c614c2d79c0c318a8119cd8","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T14:34:02Z","title_canon_sha256":"bb78a8268be84c0887da3c089047e9ee7733ad9be2e58a02bb151ff421aedaa2"},"schema_version":"1.0","source":{"id":"2403.19462","kind":"arxiv","version":1}},"canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142009494b428dc5e4a7366937ffbb681bcb924ab8732feef22778db5701d635","first_computed_at":"2026-07-05T08:01:49.238374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:49.238374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N/eHFdoRMKStLa9jR1TqMQIEPw3NdPRJxWXNm+iFc4DP9+79JJOTs79kGnkvYGt+/HraG6nUWEACd8dhr9/XAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:49.238848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19462","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0fbc1ea039720fc2b2cc53e5f381b3da45c991821c0b464c633dde47e16021f","sha256:6d001c1a46104c4dff5d2a78ebdc5ac3a797105387e2e0982000e0f62ea34bba"],"state_sha256":"447a36d80dc70054eb43a95c5ecd5289662728a6b36c2659a2ead1586f9ccdbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KoRMAf/rXti56N/rgaRJfEI9E1qBo6pKwkVhKWbiFXIDg3PXbW2k2UFyxxTpmAOmtIwY6wfVfPrqBr3TDiSzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T08:09:03.548175Z","bundle_sha256":"3cafe1639af56420564e60f2dcf33624a339852dfd0dd20adc9de79163b6809f"}}