{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AW4GZPZDBURNRDFL5EUU5DFHEQ","short_pith_number":"pith:AW4GZPZD","canonical_record":{"source":{"id":"2608.01717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T05:28:37Z","cross_cats_sorted":[],"title_canon_sha256":"f08a73c5429f858d374ee835a9450e323642e6f24c141d3c238ba8498168e9c5","abstract_canon_sha256":"eeaf74cc0473697ab02bb972c39bc20c079784cc67278cf5baf753aacac0aded"},"schema_version":"1.0"},"canonical_sha256":"05b86cbf230d22d88cabe9294e8ca7240c858f588c11acc5f6fcf2298a935034","source":{"kind":"arxiv","id":"2608.01717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01717","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01717v1","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01717","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"AW4GZPZDBURN","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"AW4GZPZDBURNRDFL","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"AW4GZPZD","created_at":"2026-08-04T02:06:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AW4GZPZDBURNRDFL5EUU5DFHEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T05:28:37Z","cross_cats_sorted":[],"title_canon_sha256":"f08a73c5429f858d374ee835a9450e323642e6f24c141d3c238ba8498168e9c5","abstract_canon_sha256":"eeaf74cc0473697ab02bb972c39bc20c079784cc67278cf5baf753aacac0aded"},"schema_version":"1.0"},"canonical_sha256":"05b86cbf230d22d88cabe9294e8ca7240c858f588c11acc5f6fcf2298a935034","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:36.998708Z","signature_b64":"tD8BMXHbw+FRflrWzl7kuTn+kfsPCnS954ckx5yIBekrfwSEjT4175vqNuC3CPyIjCNhPWuNzhLKZeaObz7DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05b86cbf230d22d88cabe9294e8ca7240c858f588c11acc5f6fcf2298a935034","last_reissued_at":"2026-08-04T02:06:36.997085Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:36.997085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01717","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":"2026-08-04T02:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtehUKb3RKEjeiBdBiAMjE1IO0c2eqPHUhGktv8sln5vOuH15FpCSwfQsOhiymNBQvxHJ69pAA0uOKGZprN+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:09:08.776335Z"},"content_sha256":"5a2a4387c777701f94bcb9a5857d594ca2a34586da6780cda51267f1ac0f9155","schema_version":"1.0","event_id":"sha256:5a2a4387c777701f94bcb9a5857d594ca2a34586da6780cda51267f1ac0f9155"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AW4GZPZDBURNRDFL5EUU5DFHEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jimyeong Kim, Jungmin Ko, Wonjong Rhee, Wonseok Lee","submitted_at":"2026-08-03T05:28:37Z","abstract_excerpt":"Recent reinforcement learning methods for diffusion large language models (dLLMs) commonly rely on on-policy rollouts generated by the target dLLM itself. When successful on-policy rollouts are scarce, however, on-policy training may receive little positive reward and make only limited progress. To mitigate this problem, we explore incorporating higher-reward rollouts generated by a stronger external policy alongside on-policy rollouts from the target dLLM. However, directly incorporating these external rollouts introduces two practical challenges: differences in rollout length and instability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01717","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/2608.01717/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":"2026-08-04T02:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0PC9/qCMzJcxPqHu75styqiJvCTiy22FxO/hkz1erDXX1DQfIoxLnUsQQzl5Jbgd3Z7gBPlSDocJkd2LMBfiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:09:08.776858Z"},"content_sha256":"8e11ff6bc4fb459023fd15ff2dcfe8616a6a2d8e6ea1619a3e75fcfab463943b","schema_version":"1.0","event_id":"sha256:8e11ff6bc4fb459023fd15ff2dcfe8616a6a2d8e6ea1619a3e75fcfab463943b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ/bundle.json","state_url":"https://pith.science/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ/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":"2026-08-05T09:09:08Z","links":{"resolver":"https://pith.science/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ","bundle":"https://pith.science/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ/bundle.json","state":"https://pith.science/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AW4GZPZDBURNRDFL5EUU5DFHEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AW4GZPZDBURNRDFL5EUU5DFHEQ","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":"eeaf74cc0473697ab02bb972c39bc20c079784cc67278cf5baf753aacac0aded","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T05:28:37Z","title_canon_sha256":"f08a73c5429f858d374ee835a9450e323642e6f24c141d3c238ba8498168e9c5"},"schema_version":"1.0","source":{"id":"2608.01717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01717","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01717v1","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01717","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"AW4GZPZDBURN","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"AW4GZPZDBURNRDFL","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"AW4GZPZD","created_at":"2026-08-04T02:06:36Z"}],"graph_snapshots":[{"event_id":"sha256:8e11ff6bc4fb459023fd15ff2dcfe8616a6a2d8e6ea1619a3e75fcfab463943b","target":"graph","created_at":"2026-08-04T02:06:36Z","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/2608.01717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent reinforcement learning methods for diffusion large language models (dLLMs) commonly rely on on-policy rollouts generated by the target dLLM itself. When successful on-policy rollouts are scarce, however, on-policy training may receive little positive reward and make only limited progress. To mitigate this problem, we explore incorporating higher-reward rollouts generated by a stronger external policy alongside on-policy rollouts from the target dLLM. However, directly incorporating these external rollouts introduces two practical challenges: differences in rollout length and instability","authors_text":"Jimyeong Kim, Jungmin Ko, Wonjong Rhee, Wonseok Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T05:28:37Z","title":"Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01717","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":"sha256:5a2a4387c777701f94bcb9a5857d594ca2a34586da6780cda51267f1ac0f9155","target":"record","created_at":"2026-08-04T02:06:36Z","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":"eeaf74cc0473697ab02bb972c39bc20c079784cc67278cf5baf753aacac0aded","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T05:28:37Z","title_canon_sha256":"f08a73c5429f858d374ee835a9450e323642e6f24c141d3c238ba8498168e9c5"},"schema_version":"1.0","source":{"id":"2608.01717","kind":"arxiv","version":1}},"canonical_sha256":"05b86cbf230d22d88cabe9294e8ca7240c858f588c11acc5f6fcf2298a935034","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05b86cbf230d22d88cabe9294e8ca7240c858f588c11acc5f6fcf2298a935034","first_computed_at":"2026-08-04T02:06:36.997085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:06:36.997085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tD8BMXHbw+FRflrWzl7kuTn+kfsPCnS954ckx5yIBekrfwSEjT4175vqNuC3CPyIjCNhPWuNzhLKZeaObz7DBg==","signature_status":"signed_v1","signed_at":"2026-08-04T02:06:36.998708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a2a4387c777701f94bcb9a5857d594ca2a34586da6780cda51267f1ac0f9155","sha256:8e11ff6bc4fb459023fd15ff2dcfe8616a6a2d8e6ea1619a3e75fcfab463943b"],"state_sha256":"bc42716e9da73af35f51cdb57b0daa5b0326d6616dc3a5db8cdcc47ef7ba1616"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mrxt3CniYn2lV6b1cvnyH3WzVKo26lfMaSDanF/XcGs8eZUcGi9dAlvFIXiGwWsQroTWcc0X1WTw7ixN4/UUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:09:08.781400Z","bundle_sha256":"c6cd637c16e0dae68d5e6bbe7bc7f395e5b672f3cc7c6f60590b237dc658ebe2"}}