{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LIEXP5Z7FZQWH5B64PVME6RNY5","short_pith_number":"pith:LIEXP5Z7","canonical_record":{"source":{"id":"2401.09681","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T02:21:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5623c1d4a6170c55f39772ffa3b8a8c6536af6c4a3bdadfda5ca82c385f21cf5","abstract_canon_sha256":"e4cc35e3aa2f6d0e8579d2d325fd386519690312c66889d2bb5398d293b736ec"},"schema_version":"1.0"},"canonical_sha256":"5a0977f73f2e6163f43ee3eac27a2dc75118e193dc92737aa945ed6403b0598f","source":{"kind":"arxiv","id":"2401.09681","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09681","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09681v2","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09681","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"LIEXP5Z7FZQW","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"LIEXP5Z7FZQWH5B6","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"LIEXP5Z7","created_at":"2026-07-05T08:27:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LIEXP5Z7FZQWH5B64PVME6RNY5","target":"record","payload":{"canonical_record":{"source":{"id":"2401.09681","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T02:21:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5623c1d4a6170c55f39772ffa3b8a8c6536af6c4a3bdadfda5ca82c385f21cf5","abstract_canon_sha256":"e4cc35e3aa2f6d0e8579d2d325fd386519690312c66889d2bb5398d293b736ec"},"schema_version":"1.0"},"canonical_sha256":"5a0977f73f2e6163f43ee3eac27a2dc75118e193dc92737aa945ed6403b0598f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:24.357954Z","signature_b64":"O2+/6DN9DDLkT7A+gU0F8L555sLYhJ3+Tzhhl0UBm5YJPHqFJ0H8WJat83825pebmGm73EKtH2Ytv6bKVsf6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a0977f73f2e6163f43ee3eac27a2dc75118e193dc92737aa945ed6403b0598f","last_reissued_at":"2026-07-05T08:27:24.357501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:24.357501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.09681","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":"2026-07-05T08:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I28GlMJc2TFZ8pBeIu+xbShdUw5plI9suZ7CFreFBdcG+IOwgG1E1GK6JJ5oKhf617EeSHchHd+DF18bqT6HCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:01:57.332043Z"},"content_sha256":"de7bddc0def9b8ad3fd64ad5b14385a1ad1ac79f6aa52c7b936ef18544ed2fd3","schema_version":"1.0","event_id":"sha256:de7bddc0def9b8ad3fd64ad5b14385a1ad1ac79f6aa52c7b936ef18544ed2fd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LIEXP5Z7FZQWH5B64PVME6RNY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Density Ratios for Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayush Sekhari, Dylan J. Foster, Nan Jiang, Philip Amortila, Tengyang Xie","submitted_at":"2024-01-18T02:21:06Z","abstract_excerpt":"The theories of offline and online reinforcement learning, despite having evolved in parallel, have begun to show signs of the possibility for a unification, with algorithms and analysis techniques for one setting often having natural counterparts in the other. However, the notion of density ratio modeling, an emerging paradigm in offline RL, has been largely absent from online RL, perhaps for good reason: the very existence and boundedness of density ratios relies on access to an exploratory dataset with good coverage, but the core challenge in online RL is to collect such a dataset without h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09681","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/2401.09681/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":"2026-07-05T08:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijTLMIAOEP+VMKhJCxWC4NwV+uQAkmbfgh4a0JV6G8TizJ/d1gRn16wxpqvdXT/NENYuxWvmhLHeVOY5AnHgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:01:57.332535Z"},"content_sha256":"5ec23b627998ee2ad0a58a1e6de5b269abe014368e664754b6d72a5ade0744e5","schema_version":"1.0","event_id":"sha256:5ec23b627998ee2ad0a58a1e6de5b269abe014368e664754b6d72a5ade0744e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIEXP5Z7FZQWH5B64PVME6RNY5/bundle.json","state_url":"https://pith.science/pith/LIEXP5Z7FZQWH5B64PVME6RNY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIEXP5Z7FZQWH5B64PVME6RNY5/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":"2026-08-08T15:01:57Z","links":{"resolver":"https://pith.science/pith/LIEXP5Z7FZQWH5B64PVME6RNY5","bundle":"https://pith.science/pith/LIEXP5Z7FZQWH5B64PVME6RNY5/bundle.json","state":"https://pith.science/pith/LIEXP5Z7FZQWH5B64PVME6RNY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIEXP5Z7FZQWH5B64PVME6RNY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LIEXP5Z7FZQWH5B64PVME6RNY5","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":"e4cc35e3aa2f6d0e8579d2d325fd386519690312c66889d2bb5398d293b736ec","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T02:21:06Z","title_canon_sha256":"5623c1d4a6170c55f39772ffa3b8a8c6536af6c4a3bdadfda5ca82c385f21cf5"},"schema_version":"1.0","source":{"id":"2401.09681","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09681","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09681v2","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09681","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"LIEXP5Z7FZQW","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"LIEXP5Z7FZQWH5B6","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"LIEXP5Z7","created_at":"2026-07-05T08:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:5ec23b627998ee2ad0a58a1e6de5b269abe014368e664754b6d72a5ade0744e5","target":"graph","created_at":"2026-07-05T08:27:24Z","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/2401.09681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The theories of offline and online reinforcement learning, despite having evolved in parallel, have begun to show signs of the possibility for a unification, with algorithms and analysis techniques for one setting often having natural counterparts in the other. However, the notion of density ratio modeling, an emerging paradigm in offline RL, has been largely absent from online RL, perhaps for good reason: the very existence and boundedness of density ratios relies on access to an exploratory dataset with good coverage, but the core challenge in online RL is to collect such a dataset without h","authors_text":"Ayush Sekhari, Dylan J. Foster, Nan Jiang, Philip Amortila, Tengyang Xie","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T02:21:06Z","title":"Harnessing Density Ratios for Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09681","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:de7bddc0def9b8ad3fd64ad5b14385a1ad1ac79f6aa52c7b936ef18544ed2fd3","target":"record","created_at":"2026-07-05T08:27:24Z","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":"e4cc35e3aa2f6d0e8579d2d325fd386519690312c66889d2bb5398d293b736ec","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T02:21:06Z","title_canon_sha256":"5623c1d4a6170c55f39772ffa3b8a8c6536af6c4a3bdadfda5ca82c385f21cf5"},"schema_version":"1.0","source":{"id":"2401.09681","kind":"arxiv","version":2}},"canonical_sha256":"5a0977f73f2e6163f43ee3eac27a2dc75118e193dc92737aa945ed6403b0598f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a0977f73f2e6163f43ee3eac27a2dc75118e193dc92737aa945ed6403b0598f","first_computed_at":"2026-07-05T08:27:24.357501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:24.357501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O2+/6DN9DDLkT7A+gU0F8L555sLYhJ3+Tzhhl0UBm5YJPHqFJ0H8WJat83825pebmGm73EKtH2Ytv6bKVsf6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:24.357954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09681","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de7bddc0def9b8ad3fd64ad5b14385a1ad1ac79f6aa52c7b936ef18544ed2fd3","sha256:5ec23b627998ee2ad0a58a1e6de5b269abe014368e664754b6d72a5ade0744e5"],"state_sha256":"15a8e18c939e74d8c1e7fae78f9eaa556e89ed3d2d22d0a195577b9cdf07022e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kig55m7rkcK69LhvVi/NWXDGLAxpUSYiKf+PajH/7CAPBItM0+vmN0W4OVZsKBDWf1LnG7TeGguF0AE9IWUNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:01:57.336587Z","bundle_sha256":"824a059fb908a726b255b87338c9ab40a8de47322ac35cccfefca8250dc005b3"}}