{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:G6HLRYCYAGMZL2QOJ3JWNMAYBL","short_pith_number":"pith:G6HLRYCY","canonical_record":{"source":{"id":"2607.17247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T13:32:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df46f1ff423f735c4c8eb335bc73dd2b4bf5de544743e19a1b6730074705c929","abstract_canon_sha256":"296d181e3f1efa597eb0210f3efa53b87347bf9d98ce9a58d4d69497d68aaae2"},"schema_version":"1.0"},"canonical_sha256":"378eb8e058019995ea0e4ed366b0180ae942cfb87fec7386ca1fb364fd90009d","source":{"kind":"arxiv","id":"2607.17247","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17247","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17247v1","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17247","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"G6HLRYCYAGMZ","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"G6HLRYCYAGMZL2QO","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"G6HLRYCY","created_at":"2026-07-21T01:21:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:G6HLRYCYAGMZL2QOJ3JWNMAYBL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T13:32:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df46f1ff423f735c4c8eb335bc73dd2b4bf5de544743e19a1b6730074705c929","abstract_canon_sha256":"296d181e3f1efa597eb0210f3efa53b87347bf9d98ce9a58d4d69497d68aaae2"},"schema_version":"1.0"},"canonical_sha256":"378eb8e058019995ea0e4ed366b0180ae942cfb87fec7386ca1fb364fd90009d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:23.746478Z","signature_b64":"B8Izm/9F2uF0+W10U5am+Cn/4go9Brn38MCaB8qRmTBkcTkTykdXRPa5zQKBELbowSlTxWTZdnqk+dKIxuebAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"378eb8e058019995ea0e4ed366b0180ae942cfb87fec7386ca1fb364fd90009d","last_reissued_at":"2026-07-21T01:21:23.745644Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:23.745644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17247","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":"2026-07-21T01:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZfSI7zaG5oSFW0rNjm7JIy9kkKMxXscokdYTzQVuI8Ag+oIR64Um2UAJaamvTcrO1T0xa7ip8hXmX/9nPj1/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:16:04.099125Z"},"content_sha256":"23735b2bf91754a3c7b4e05aab21df9602ce1b7781bc4f4737b63b461faaa71a","schema_version":"1.0","event_id":"sha256:23735b2bf91754a3c7b4e05aab21df9602ce1b7781bc4f4737b63b461faaa71a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:G6HLRYCYAGMZL2QOJ3JWNMAYBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilled Reinforcement Learning for LLM Post-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Wang, Ge Lan, Hexuan Deng, Jionghao Bai, Yining Zhang, Yue Wang, Zhaochun Li","submitted_at":"2026-07-19T13:32:54Z","abstract_excerpt":"Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17247","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/2607.17247/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":"2026-07-21T01:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xay9xEaw4MWAI+LNH9N6bineQALuedlHEqriiCYoKBfn+brI9hLc59fP6yp35ti2mDGtITXC78OWMCLJRf7xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:16:04.099726Z"},"content_sha256":"8dd4bec928bfbfd485c1b0dae3781aa4ef2a5b7644593ba7ca74314e488a4e9c","schema_version":"1.0","event_id":"sha256:8dd4bec928bfbfd485c1b0dae3781aa4ef2a5b7644593ba7ca74314e488a4e9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL/bundle.json","state_url":"https://pith.science/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL/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":"2026-08-05T15:16:04Z","links":{"resolver":"https://pith.science/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL","bundle":"https://pith.science/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL/bundle.json","state":"https://pith.science/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6HLRYCYAGMZL2QOJ3JWNMAYBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G6HLRYCYAGMZL2QOJ3JWNMAYBL","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":"296d181e3f1efa597eb0210f3efa53b87347bf9d98ce9a58d4d69497d68aaae2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T13:32:54Z","title_canon_sha256":"df46f1ff423f735c4c8eb335bc73dd2b4bf5de544743e19a1b6730074705c929"},"schema_version":"1.0","source":{"id":"2607.17247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17247","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17247v1","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17247","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"G6HLRYCYAGMZ","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"G6HLRYCYAGMZL2QO","created_at":"2026-07-21T01:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"G6HLRYCY","created_at":"2026-07-21T01:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:8dd4bec928bfbfd485c1b0dae3781aa4ef2a5b7644593ba7ca74314e488a4e9c","target":"graph","created_at":"2026-07-21T01:21:23Z","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/2607.17247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restric","authors_text":"Chen Wang, Ge Lan, Hexuan Deng, Jionghao Bai, Yining Zhang, Yue Wang, Zhaochun Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T13:32:54Z","title":"Distilled Reinforcement Learning for LLM Post-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17247","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":"sha256:23735b2bf91754a3c7b4e05aab21df9602ce1b7781bc4f4737b63b461faaa71a","target":"record","created_at":"2026-07-21T01:21:23Z","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":"296d181e3f1efa597eb0210f3efa53b87347bf9d98ce9a58d4d69497d68aaae2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T13:32:54Z","title_canon_sha256":"df46f1ff423f735c4c8eb335bc73dd2b4bf5de544743e19a1b6730074705c929"},"schema_version":"1.0","source":{"id":"2607.17247","kind":"arxiv","version":1}},"canonical_sha256":"378eb8e058019995ea0e4ed366b0180ae942cfb87fec7386ca1fb364fd90009d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"378eb8e058019995ea0e4ed366b0180ae942cfb87fec7386ca1fb364fd90009d","first_computed_at":"2026-07-21T01:21:23.745644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:23.745644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B8Izm/9F2uF0+W10U5am+Cn/4go9Brn38MCaB8qRmTBkcTkTykdXRPa5zQKBELbowSlTxWTZdnqk+dKIxuebAA==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:23.746478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23735b2bf91754a3c7b4e05aab21df9602ce1b7781bc4f4737b63b461faaa71a","sha256:8dd4bec928bfbfd485c1b0dae3781aa4ef2a5b7644593ba7ca74314e488a4e9c"],"state_sha256":"77e03106e382ff4e5f6e169196d2249119f2aae60786557e2ea79765f2d6183f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72lIfl8UN6Pbjtzl+uHUPibDTEws0E7+nWDvAEks799v1tWpmMpQxugTLI+e8QKmpCtvgl3hoED0EkYSScWgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:16:04.104694Z","bundle_sha256":"e18287e235c550ff4235b9b82cfa6f4af0e6a959423bd47a5a542a22712ee5ba"}}