{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ORQJ722U2YQBNA3JT5F2HZM664","short_pith_number":"pith:ORQJ722U","canonical_record":{"source":{"id":"2608.00782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T17:29:14Z","cross_cats_sorted":[],"title_canon_sha256":"193d89711f9a497e7e1bd90bd51c7a0b4d4e501528f73a758dd3908a72498514","abstract_canon_sha256":"b489c29095c02f53086f8567a24b3c3b37a20ab5769c260bad922a2f30bbf241"},"schema_version":"1.0"},"canonical_sha256":"74609feb54d6201683699f4ba3e59ef703271aecd57027b9581285efa4e6c96c","source":{"kind":"arxiv","id":"2608.00782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00782","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00782v1","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00782","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"ORQJ722U2YQB","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"pith_short_16","alias_value":"ORQJ722U2YQBNA3J","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"pith_short_8","alias_value":"ORQJ722U","created_at":"2026-08-04T01:55:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ORQJ722U2YQBNA3JT5F2HZM664","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T17:29:14Z","cross_cats_sorted":[],"title_canon_sha256":"193d89711f9a497e7e1bd90bd51c7a0b4d4e501528f73a758dd3908a72498514","abstract_canon_sha256":"b489c29095c02f53086f8567a24b3c3b37a20ab5769c260bad922a2f30bbf241"},"schema_version":"1.0"},"canonical_sha256":"74609feb54d6201683699f4ba3e59ef703271aecd57027b9581285efa4e6c96c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:55:05.229644Z","signature_b64":"kuszw1D7jJzJDsvhiBUAtHEfzl693/dJ7/boZuZRec3oR0BZU8pz1vddk8c/Pb3yqjGTG/2MsT9D5VhJgw3yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74609feb54d6201683699f4ba3e59ef703271aecd57027b9581285efa4e6c96c","last_reissued_at":"2026-08-04T01:55:05.227997Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:55:05.227997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00782","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":"2026-08-04T01:55:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/zQTX0duj7iTi0/0HpbGhlTK6R4jtM8PGEaTbKGPe+jobhTmsC68H5EeVs3i5XUxw5SKKTVW+oAX0zU2rnbjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:35:57.039040Z"},"content_sha256":"9d79fa50390039de7515cb4fd560fe681a6e6bc3dd3b06d370fe9cde3963ff25","schema_version":"1.0","event_id":"sha256:9d79fa50390039de7515cb4fd560fe681a6e6bc3dd3b06d370fe9cde3963ff25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ORQJ722U2YQBNA3JT5F2HZM664","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Hongyan Hao, Jinwei Xiao, Qi Gu, Renren Jin, Xunliang Cai, Yueqing Sun, Yuxin Liu, Yu Yang, Zhengxi Lu, Zhiyuan Yao, Zhuowen Han","submitted_at":"2026-08-01T17:29:14Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO) is widely adopted, it suffers from sparse reward signals and loses gradients entirely when all responses within a group receive identical rewards. On-policy distillation (OPD) offers a natural remedy by providing dense, token-level supervision from a teacher model. However, naively combining GRPO with OPD leads to degraded performance, due to three underlying causes: not all samples benefit from distillation; fittin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00782","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/2608.00782/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":"2026-08-04T01:55:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAVdtXFsKdj2qLoHnIsPpHasMG0CpFcThiWQKiu2mUrdxMd+QItetCVeYd+U4d8wYG/tHpA1jIh5136+vUGkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:35:57.039541Z"},"content_sha256":"1673bb9e3463d762b19ab1dd91a6e49984bf425b66e3ebbf8c7fe3482d8a5dc6","schema_version":"1.0","event_id":"sha256:1673bb9e3463d762b19ab1dd91a6e49984bf425b66e3ebbf8c7fe3482d8a5dc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORQJ722U2YQBNA3JT5F2HZM664/bundle.json","state_url":"https://pith.science/pith/ORQJ722U2YQBNA3JT5F2HZM664/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORQJ722U2YQBNA3JT5F2HZM664/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":"2026-08-05T10:35:57Z","links":{"resolver":"https://pith.science/pith/ORQJ722U2YQBNA3JT5F2HZM664","bundle":"https://pith.science/pith/ORQJ722U2YQBNA3JT5F2HZM664/bundle.json","state":"https://pith.science/pith/ORQJ722U2YQBNA3JT5F2HZM664/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORQJ722U2YQBNA3JT5F2HZM664/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ORQJ722U2YQBNA3JT5F2HZM664","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":"b489c29095c02f53086f8567a24b3c3b37a20ab5769c260bad922a2f30bbf241","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T17:29:14Z","title_canon_sha256":"193d89711f9a497e7e1bd90bd51c7a0b4d4e501528f73a758dd3908a72498514"},"schema_version":"1.0","source":{"id":"2608.00782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00782","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00782v1","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00782","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"ORQJ722U2YQB","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"pith_short_16","alias_value":"ORQJ722U2YQBNA3J","created_at":"2026-08-04T01:55:05Z"},{"alias_kind":"pith_short_8","alias_value":"ORQJ722U","created_at":"2026-08-04T01:55:05Z"}],"graph_snapshots":[{"event_id":"sha256:1673bb9e3463d762b19ab1dd91a6e49984bf425b66e3ebbf8c7fe3482d8a5dc6","target":"graph","created_at":"2026-08-04T01:55:05Z","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/2608.00782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models (LLMs). While Group Relative Policy Optimization (GRPO) is widely adopted, it suffers from sparse reward signals and loses gradients entirely when all responses within a group receive identical rewards. On-policy distillation (OPD) offers a natural remedy by providing dense, token-level supervision from a teacher model. However, naively combining GRPO with OPD leads to degraded performance, due to three underlying causes: not all samples benefit from distillation; fittin","authors_text":"Deyi Xiong, Hongyan Hao, Jinwei Xiao, Qi Gu, Renren Jin, Xunliang Cai, Yueqing Sun, Yuxin Liu, Yu Yang, Zhengxi Lu, Zhiyuan Yao, Zhuowen Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T17:29:14Z","title":"Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00782","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":"sha256:9d79fa50390039de7515cb4fd560fe681a6e6bc3dd3b06d370fe9cde3963ff25","target":"record","created_at":"2026-08-04T01:55:05Z","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":"b489c29095c02f53086f8567a24b3c3b37a20ab5769c260bad922a2f30bbf241","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-01T17:29:14Z","title_canon_sha256":"193d89711f9a497e7e1bd90bd51c7a0b4d4e501528f73a758dd3908a72498514"},"schema_version":"1.0","source":{"id":"2608.00782","kind":"arxiv","version":1}},"canonical_sha256":"74609feb54d6201683699f4ba3e59ef703271aecd57027b9581285efa4e6c96c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74609feb54d6201683699f4ba3e59ef703271aecd57027b9581285efa4e6c96c","first_computed_at":"2026-08-04T01:55:05.227997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:55:05.227997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kuszw1D7jJzJDsvhiBUAtHEfzl693/dJ7/boZuZRec3oR0BZU8pz1vddk8c/Pb3yqjGTG/2MsT9D5VhJgw3yBg==","signature_status":"signed_v1","signed_at":"2026-08-04T01:55:05.229644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d79fa50390039de7515cb4fd560fe681a6e6bc3dd3b06d370fe9cde3963ff25","sha256:1673bb9e3463d762b19ab1dd91a6e49984bf425b66e3ebbf8c7fe3482d8a5dc6"],"state_sha256":"1fe72c2f5e51fb390f240f087c3dea1fd1326653e93e28ab89915723f2a68044"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4SKLfVpphg0L7B5V9V59DWN12lP87h0Wy1gwGuQRQCfqORdTVkQNZlxswI2dhV9lRjQPqAUnth9eNZT+eq8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:35:57.043977Z","bundle_sha256":"6df84c937836f4e9368723637fba1153272a83d942b453bfd3c057c13e1b7d3e"}}