{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:L3VYRN4EEE46DHVUGOKDGJRR7T","short_pith_number":"pith:L3VYRN4E","canonical_record":{"source":{"id":"2212.00639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T16:40:11Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"86b7e6a149c6db14a7acf8c99662205ef1de7a84e05131bd408870a4304a25b3","abstract_canon_sha256":"96ec5d35825daf8bec6980dbba4d9b912b8af931b5c7b1ff2bb219d4a6c72d0e"},"schema_version":"1.0"},"canonical_sha256":"5eeb88b7842139e19eb43394332631fccb52b38507f92691214c1916fc64814b","source":{"kind":"arxiv","id":"2212.00639","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00639","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00639v2","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00639","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"L3VYRN4EEE46","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"L3VYRN4EEE46DHVU","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"L3VYRN4E","created_at":"2026-07-05T05:21:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:L3VYRN4EEE46DHVUGOKDGJRR7T","target":"record","payload":{"canonical_record":{"source":{"id":"2212.00639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T16:40:11Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"86b7e6a149c6db14a7acf8c99662205ef1de7a84e05131bd408870a4304a25b3","abstract_canon_sha256":"96ec5d35825daf8bec6980dbba4d9b912b8af931b5c7b1ff2bb219d4a6c72d0e"},"schema_version":"1.0"},"canonical_sha256":"5eeb88b7842139e19eb43394332631fccb52b38507f92691214c1916fc64814b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:45.823141Z","signature_b64":"p8w1kGLdCVSzc9fj2sgU+aDhkJJNxWz2ntyOUFjVmxTmzTgndaQDQcHrZKF+VHSIEeWcJOLtPSy1kMArv1d9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eeb88b7842139e19eb43394332631fccb52b38507f92691214c1916fc64814b","last_reissued_at":"2026-07-05T05:21:45.822625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:45.822625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.00639","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":"2026-07-05T05:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Qsd0uT/QtKBmrj4Jhbmi4yYx6++pQiB3PnVk+ggGDqk7f8VtcXHjSZDCQfYQeBdLXvaQXHccbAExFMaV8BVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T21:13:45.443918Z"},"content_sha256":"b6f6c97f5357c08b0fd9a5b6f2b050d9ea599601b84e8a967a80c0d7f4f66d04","schema_version":"1.0","event_id":"sha256:b6f6c97f5357c08b0fd9a5b6f2b050d9ea599601b84e8a967a80c0d7f4f66d04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:L3VYRN4EEE46DHVUGOKDGJRR7T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Launchpad: Learning to Schedule Using Offline and Online RL Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Andrew Grimshaw, Jake Grigsby, Vanamala Venkataswamy, Yanjun Qi","submitted_at":"2022-12-01T16:40:11Z","abstract_excerpt":"Deep reinforcement learning algorithms have succeeded in several challenging domains. Classic Online RL job schedulers can learn efficient scheduling strategies but often takes thousands of timesteps to explore the environment and adapt from a randomly initialized DNN policy. Existing RL schedulers overlook the importance of learning from historical data and improving upon custom heuristic policies. Offline reinforcement learning presents the prospect of policy optimization from pre-recorded datasets without online environment interaction. Following the recent success of data-driven learning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00639","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/2212.00639/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":"2026-07-05T05:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGLdBJbKA/RJXqgp9cEWccxxmfZNqAjIN42MYiTLm4rPcvKEs7DD4O3dRrxFDtnQj75asMFyC1KTVbO4CVjfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T21:13:45.444281Z"},"content_sha256":"c62f4749b5fad08774682459b8909898f9d60a0599820b0847be913395b840be","schema_version":"1.0","event_id":"sha256:c62f4749b5fad08774682459b8909898f9d60a0599820b0847be913395b840be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3VYRN4EEE46DHVUGOKDGJRR7T/bundle.json","state_url":"https://pith.science/pith/L3VYRN4EEE46DHVUGOKDGJRR7T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3VYRN4EEE46DHVUGOKDGJRR7T/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":"2026-07-26T21:13:45Z","links":{"resolver":"https://pith.science/pith/L3VYRN4EEE46DHVUGOKDGJRR7T","bundle":"https://pith.science/pith/L3VYRN4EEE46DHVUGOKDGJRR7T/bundle.json","state":"https://pith.science/pith/L3VYRN4EEE46DHVUGOKDGJRR7T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3VYRN4EEE46DHVUGOKDGJRR7T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:L3VYRN4EEE46DHVUGOKDGJRR7T","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":"96ec5d35825daf8bec6980dbba4d9b912b8af931b5c7b1ff2bb219d4a6c72d0e","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T16:40:11Z","title_canon_sha256":"86b7e6a149c6db14a7acf8c99662205ef1de7a84e05131bd408870a4304a25b3"},"schema_version":"1.0","source":{"id":"2212.00639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00639","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00639v2","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00639","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"L3VYRN4EEE46","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"L3VYRN4EEE46DHVU","created_at":"2026-07-05T05:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"L3VYRN4E","created_at":"2026-07-05T05:21:45Z"}],"graph_snapshots":[{"event_id":"sha256:c62f4749b5fad08774682459b8909898f9d60a0599820b0847be913395b840be","target":"graph","created_at":"2026-07-05T05:21:45Z","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/2212.00639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning algorithms have succeeded in several challenging domains. Classic Online RL job schedulers can learn efficient scheduling strategies but often takes thousands of timesteps to explore the environment and adapt from a randomly initialized DNN policy. Existing RL schedulers overlook the importance of learning from historical data and improving upon custom heuristic policies. Offline reinforcement learning presents the prospect of policy optimization from pre-recorded datasets without online environment interaction. Following the recent success of data-driven learning, ","authors_text":"Andrew Grimshaw, Jake Grigsby, Vanamala Venkataswamy, Yanjun Qi","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T16:40:11Z","title":"Launchpad: Learning to Schedule Using Offline and Online RL Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00639","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:b6f6c97f5357c08b0fd9a5b6f2b050d9ea599601b84e8a967a80c0d7f4f66d04","target":"record","created_at":"2026-07-05T05:21:45Z","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":"96ec5d35825daf8bec6980dbba4d9b912b8af931b5c7b1ff2bb219d4a6c72d0e","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T16:40:11Z","title_canon_sha256":"86b7e6a149c6db14a7acf8c99662205ef1de7a84e05131bd408870a4304a25b3"},"schema_version":"1.0","source":{"id":"2212.00639","kind":"arxiv","version":2}},"canonical_sha256":"5eeb88b7842139e19eb43394332631fccb52b38507f92691214c1916fc64814b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eeb88b7842139e19eb43394332631fccb52b38507f92691214c1916fc64814b","first_computed_at":"2026-07-05T05:21:45.822625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:45.822625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8w1kGLdCVSzc9fj2sgU+aDhkJJNxWz2ntyOUFjVmxTmzTgndaQDQcHrZKF+VHSIEeWcJOLtPSy1kMArv1d9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:45.823141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f6c97f5357c08b0fd9a5b6f2b050d9ea599601b84e8a967a80c0d7f4f66d04","sha256:c62f4749b5fad08774682459b8909898f9d60a0599820b0847be913395b840be"],"state_sha256":"b6f0b117569ef462036f0bff1fc2da1b763a2448ade9a840e90921d18ec3e353"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LiHCi2KAF6Da7ZZshOir4kOIiDKTUkEoa/koZg5EbcaTfGKWFr26FrusaeCQUZN3NhrEiCMB5/jX/nwpSCiEDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T21:13:45.446417Z","bundle_sha256":"52910c930a7eae771aac2bbfc53a561063a4532899500dfa7e8e6492ca019b84"}}