{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UDFRFK6T75MQBXNQQPPLKS2SLL","short_pith_number":"pith:UDFRFK6T","canonical_record":{"source":{"id":"2212.03864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T02:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"ab87930f05a3bb7c9fe267ec088eb7ea25dceab65f6ec47b38978b7327a8bad0","abstract_canon_sha256":"dff7c370b011a66c172b6946de73c9195799a18f360ec56c3ddcd327bc255b7e"},"schema_version":"1.0"},"canonical_sha256":"a0cb12abd3ff5900ddb083deb54b525ad19e3c666691dd16b7e02d8649644c4b","source":{"kind":"arxiv","id":"2212.03864","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03864","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03864v1","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03864","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"UDFRFK6T75MQ","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"UDFRFK6T75MQBXNQ","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"UDFRFK6T","created_at":"2026-07-05T05:23:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UDFRFK6T75MQBXNQQPPLKS2SLL","target":"record","payload":{"canonical_record":{"source":{"id":"2212.03864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T02:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"ab87930f05a3bb7c9fe267ec088eb7ea25dceab65f6ec47b38978b7327a8bad0","abstract_canon_sha256":"dff7c370b011a66c172b6946de73c9195799a18f360ec56c3ddcd327bc255b7e"},"schema_version":"1.0"},"canonical_sha256":"a0cb12abd3ff5900ddb083deb54b525ad19e3c666691dd16b7e02d8649644c4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:21.951154Z","signature_b64":"e/XPFJZeW7ClqfRj5A6lBp3x6MYqypmOqxEhJWA7KSWWTyJ8k+T3JvVnfKZeF8wtcuhtZM+ADEvjhRf2AA6hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0cb12abd3ff5900ddb083deb54b525ad19e3c666691dd16b7e02d8649644c4b","last_reissued_at":"2026-07-05T05:23:21.950776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:21.950776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.03864","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":"2026-07-05T05:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YdlVKpvfEyOBc3qKzlRHr2Kv8Tj6MAhkSs+Rbqz1SX5ULD2il1QTtVYRp2/bhjxRA3gFgAzYVMJXBvMTK9hJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:07:02.097050Z"},"content_sha256":"4a5f76c02db9b4a1a06e9d1e4109d4553b83acf4a5c38a1192f1559d2ae16443","schema_version":"1.0","event_id":"sha256:4a5f76c02db9b4a1a06e9d1e4109d4553b83acf4a5c38a1192f1559d2ae16443"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UDFRFK6T75MQBXNQQPPLKS2SLL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Offline Reinforcement Learning Help Natural Language Understanding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Donglin Wang, Yile Wang, Yue Zhang, Ziqi Zhang","submitted_at":"2022-09-15T02:55:10Z","abstract_excerpt":"Pre-training has been a useful method for learning implicit transferable knowledge and it shows the benefit of offering complementary features across different modalities. Recent work mainly focuses on the modalities such as image and text, for example, studies show that visual features learned from images can help visual-grounded language understanding. In this paper, we consider investigating the potential connection between offline reinforcement learning (RL) and language modeling (LM). Intuitively, RL and LM are similar in predicting the next states based on the current and previous states"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03864","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/2212.03864/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":"2026-07-05T05:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LcA2nKs/4huxyr3616g4uVqw7Dcp3jq2WkohNVMpAu+XoRr759mPPyM6IdeU9TyD+dqUYj+6xrFA0EnnHf73BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:07:02.097628Z"},"content_sha256":"81742681754cd79847370f2945ecb005916cac6fc48a6e3472f9b2a0ea0bfaaf","schema_version":"1.0","event_id":"sha256:81742681754cd79847370f2945ecb005916cac6fc48a6e3472f9b2a0ea0bfaaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDFRFK6T75MQBXNQQPPLKS2SLL/bundle.json","state_url":"https://pith.science/pith/UDFRFK6T75MQBXNQQPPLKS2SLL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDFRFK6T75MQBXNQQPPLKS2SLL/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":"2026-08-01T07:07:02Z","links":{"resolver":"https://pith.science/pith/UDFRFK6T75MQBXNQQPPLKS2SLL","bundle":"https://pith.science/pith/UDFRFK6T75MQBXNQQPPLKS2SLL/bundle.json","state":"https://pith.science/pith/UDFRFK6T75MQBXNQQPPLKS2SLL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDFRFK6T75MQBXNQQPPLKS2SLL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UDFRFK6T75MQBXNQQPPLKS2SLL","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":"dff7c370b011a66c172b6946de73c9195799a18f360ec56c3ddcd327bc255b7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T02:55:10Z","title_canon_sha256":"ab87930f05a3bb7c9fe267ec088eb7ea25dceab65f6ec47b38978b7327a8bad0"},"schema_version":"1.0","source":{"id":"2212.03864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03864","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03864v1","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03864","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"UDFRFK6T75MQ","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"UDFRFK6T75MQBXNQ","created_at":"2026-07-05T05:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"UDFRFK6T","created_at":"2026-07-05T05:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:81742681754cd79847370f2945ecb005916cac6fc48a6e3472f9b2a0ea0bfaaf","target":"graph","created_at":"2026-07-05T05:23:21Z","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/2212.03864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training has been a useful method for learning implicit transferable knowledge and it shows the benefit of offering complementary features across different modalities. Recent work mainly focuses on the modalities such as image and text, for example, studies show that visual features learned from images can help visual-grounded language understanding. In this paper, we consider investigating the potential connection between offline reinforcement learning (RL) and language modeling (LM). Intuitively, RL and LM are similar in predicting the next states based on the current and previous states","authors_text":"Donglin Wang, Yile Wang, Yue Zhang, Ziqi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T02:55:10Z","title":"Can Offline Reinforcement Learning Help Natural Language Understanding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03864","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":"sha256:4a5f76c02db9b4a1a06e9d1e4109d4553b83acf4a5c38a1192f1559d2ae16443","target":"record","created_at":"2026-07-05T05:23:21Z","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":"dff7c370b011a66c172b6946de73c9195799a18f360ec56c3ddcd327bc255b7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-15T02:55:10Z","title_canon_sha256":"ab87930f05a3bb7c9fe267ec088eb7ea25dceab65f6ec47b38978b7327a8bad0"},"schema_version":"1.0","source":{"id":"2212.03864","kind":"arxiv","version":1}},"canonical_sha256":"a0cb12abd3ff5900ddb083deb54b525ad19e3c666691dd16b7e02d8649644c4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0cb12abd3ff5900ddb083deb54b525ad19e3c666691dd16b7e02d8649644c4b","first_computed_at":"2026-07-05T05:23:21.950776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:21.950776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e/XPFJZeW7ClqfRj5A6lBp3x6MYqypmOqxEhJWA7KSWWTyJ8k+T3JvVnfKZeF8wtcuhtZM+ADEvjhRf2AA6hAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:21.951154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a5f76c02db9b4a1a06e9d1e4109d4553b83acf4a5c38a1192f1559d2ae16443","sha256:81742681754cd79847370f2945ecb005916cac6fc48a6e3472f9b2a0ea0bfaaf"],"state_sha256":"ea74863e7958d5bd1329dd2c9b504cee5a070e122b4093832fa3162696563f7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftOdX0eWvsMG76XV3Q1GQTgCzZxC50iPQ+ln+mIx868dJM1bl4trMH58CPR2Sq5MAJg6dIrO/r3JiVWjR8VjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:07:02.105803Z","bundle_sha256":"cffe38de357349cb557c91418bcd0dc3dd7165dfc43a678c7a4bdc457aa3fd9c"}}