{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MAX6VSMP3YAJG6EYTRAKCQI3ZF","short_pith_number":"pith:MAX6VSMP","canonical_record":{"source":{"id":"2011.09750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T10:00:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f2aab0a2845f5a63838a3618227ba31c49842777f28354f0ed6e259eecf5d6c","abstract_canon_sha256":"2e5ff161c7330b3e1de5414c7253efec9933949691f8bc7998a63242c558014e"},"schema_version":"1.0"},"canonical_sha256":"602feac98fde009378989c40a1411bc951baccd5db0a686861197170819bb050","source":{"kind":"arxiv","id":"2011.09750","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09750","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09750v1","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09750","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"MAX6VSMP3YAJ","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"MAX6VSMP3YAJG6EY","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"MAX6VSMP","created_at":"2026-07-05T01:52:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MAX6VSMP3YAJG6EYTRAKCQI3ZF","target":"record","payload":{"canonical_record":{"source":{"id":"2011.09750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T10:00:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f2aab0a2845f5a63838a3618227ba31c49842777f28354f0ed6e259eecf5d6c","abstract_canon_sha256":"2e5ff161c7330b3e1de5414c7253efec9933949691f8bc7998a63242c558014e"},"schema_version":"1.0"},"canonical_sha256":"602feac98fde009378989c40a1411bc951baccd5db0a686861197170819bb050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:51.732243Z","signature_b64":"/+zioEqSpNRAb2z/tlTBr8Uekcu62bIAKq8fNZn9VUwbDwvoK8CrZBxPqzZ60q40tpsw77aDxt+SwpsePItdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"602feac98fde009378989c40a1411bc951baccd5db0a686861197170819bb050","last_reissued_at":"2026-07-05T01:52:51.731887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:51.731887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.09750","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":"2026-07-05T01:52:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"egZEWWQz1w1Q7Oiv75NkvRYTx3NZIycM6imy90XvwnKBihGOrCyvkTEbvEHFPizzH+/iBEHv+I9k359Ic7hnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:07.761401Z"},"content_sha256":"663e028649332002101e294e7d3aab04c9d5f8f8c214a3e944bce59a88c79ac3","schema_version":"1.0","event_id":"sha256:663e028649332002101e294e7d3aab04c9d5f8f8c214a3e944bce59a88c79ac3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MAX6VSMP3YAJG6EYTRAKCQI3ZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Model Selection for Reinforcement Learning with Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Emma Brunskill, Jonathan N. Lee, Vidya Muthukumar, Weihao Kong","submitted_at":"2020-11-19T10:00:54Z","abstract_excerpt":"Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and early theoretical results on linear Markov decision processes provide regret bounds that scale with the dimension of the linear approximation. Ideally, we would like to automatically identify the minimal dimension of the approximation that is sufficient to encode an optimal policy. Towards this end, we consider the problem of model selection in RL with funct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09750","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/2011.09750/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":"2026-07-05T01:52:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XJF787ZALnxJCuI207dy32jKk/vD5FnZ8f44btTnVbx4NXCLgA94Dx8rwUksnz9qGwAZyb7l0tyOQ0lUGNzWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:07.761790Z"},"content_sha256":"fcdefe5f5dfbea05451e6c48406ff88279b461976d601bdd106c54d8d37328ea","schema_version":"1.0","event_id":"sha256:fcdefe5f5dfbea05451e6c48406ff88279b461976d601bdd106c54d8d37328ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF/bundle.json","state_url":"https://pith.science/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF/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":"2026-08-07T07:16:07Z","links":{"resolver":"https://pith.science/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF","bundle":"https://pith.science/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF/bundle.json","state":"https://pith.science/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAX6VSMP3YAJG6EYTRAKCQI3ZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MAX6VSMP3YAJG6EYTRAKCQI3ZF","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":"2e5ff161c7330b3e1de5414c7253efec9933949691f8bc7998a63242c558014e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T10:00:54Z","title_canon_sha256":"7f2aab0a2845f5a63838a3618227ba31c49842777f28354f0ed6e259eecf5d6c"},"schema_version":"1.0","source":{"id":"2011.09750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09750","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09750v1","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09750","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"MAX6VSMP3YAJ","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"MAX6VSMP3YAJG6EY","created_at":"2026-07-05T01:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"MAX6VSMP","created_at":"2026-07-05T01:52:51Z"}],"graph_snapshots":[{"event_id":"sha256:fcdefe5f5dfbea05451e6c48406ff88279b461976d601bdd106c54d8d37328ea","target":"graph","created_at":"2026-07-05T01:52:51Z","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/2011.09750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and early theoretical results on linear Markov decision processes provide regret bounds that scale with the dimension of the linear approximation. Ideally, we would like to automatically identify the minimal dimension of the approximation that is sufficient to encode an optimal policy. Towards this end, we consider the problem of model selection in RL with funct","authors_text":"Aldo Pacchiano, Emma Brunskill, Jonathan N. Lee, Vidya Muthukumar, Weihao Kong","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T10:00:54Z","title":"Online Model Selection for Reinforcement Learning with Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09750","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":"sha256:663e028649332002101e294e7d3aab04c9d5f8f8c214a3e944bce59a88c79ac3","target":"record","created_at":"2026-07-05T01:52:51Z","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":"2e5ff161c7330b3e1de5414c7253efec9933949691f8bc7998a63242c558014e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T10:00:54Z","title_canon_sha256":"7f2aab0a2845f5a63838a3618227ba31c49842777f28354f0ed6e259eecf5d6c"},"schema_version":"1.0","source":{"id":"2011.09750","kind":"arxiv","version":1}},"canonical_sha256":"602feac98fde009378989c40a1411bc951baccd5db0a686861197170819bb050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"602feac98fde009378989c40a1411bc951baccd5db0a686861197170819bb050","first_computed_at":"2026-07-05T01:52:51.731887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:52:51.731887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/+zioEqSpNRAb2z/tlTBr8Uekcu62bIAKq8fNZn9VUwbDwvoK8CrZBxPqzZ60q40tpsw77aDxt+SwpsePItdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:52:51.732243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:663e028649332002101e294e7d3aab04c9d5f8f8c214a3e944bce59a88c79ac3","sha256:fcdefe5f5dfbea05451e6c48406ff88279b461976d601bdd106c54d8d37328ea"],"state_sha256":"1399fd7b6131b2b54da184444fd39bd3277bcd6121af843b3526f9240cf07a16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUwNhaVLa9LoNic8ooV6PhD3OsxNIWqP7XNjNQIiaxRQF4ix8OWAHkrNackmfFGVzCc4oz1Rrltz+f99hrXYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:16:07.764794Z","bundle_sha256":"aad268ffa825d6f68355d20e7e2b26d48a734a2a629dcb092daad7e006a8eed5"}}