{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CJLEFONXJJRN5SP7FUQYQHHQKJ","short_pith_number":"pith:CJLEFONX","canonical_record":{"source":{"id":"2605.27765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T23:30:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"823ce2018611d67546e1d93952525598a6d42498403957450540e0294d2221df","abstract_canon_sha256":"ceaee9abbb9eb708eb48f6f0ebcb14da28ec4d801a3bfce02ffbfb4982ed5c7c"},"schema_version":"1.0"},"canonical_sha256":"125642b9b74a62dec9ff2d21881cf0527094bc652a5ae4f925e300ec7387f9a6","source":{"kind":"arxiv","id":"2605.27765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27765","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27765v1","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27765","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"CJLEFONXJJRN","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"CJLEFONXJJRN5SP7","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"CJLEFONX","created_at":"2026-05-28T01:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CJLEFONXJJRN5SP7FUQYQHHQKJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T23:30:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"823ce2018611d67546e1d93952525598a6d42498403957450540e0294d2221df","abstract_canon_sha256":"ceaee9abbb9eb708eb48f6f0ebcb14da28ec4d801a3bfce02ffbfb4982ed5c7c"},"schema_version":"1.0"},"canonical_sha256":"125642b9b74a62dec9ff2d21881cf0527094bc652a5ae4f925e300ec7387f9a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:48.330729Z","signature_b64":"54aT5sZuSYZrGl4JwoZSoaqP7kRkKcUtNqksz76RN/rellDwg3r6SPUYV316n1ax5TWMerT9CiY1QDIqKUj5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125642b9b74a62dec9ff2d21881cf0527094bc652a5ae4f925e300ec7387f9a6","last_reissued_at":"2026-05-28T01:04:48.330348Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:48.330348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27765","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":"2026-05-28T01:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBF97ADTo81SlgJL4LaXUbfFRdz0anrPHf1KADkdBiB2d9BKOZUmsAH2hUDM29bUC5KpanFmdb6m4JFVkjZfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:19:30.956111Z"},"content_sha256":"0a6df0a77bdf8768e76ac77e6005c0ca629b6235e743ccc23f4e04b46239256e","schema_version":"1.0","event_id":"sha256:0a6df0a77bdf8768e76ac77e6005c0ca629b6235e743ccc23f4e04b46239256e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CJLEFONXJJRN5SP7FUQYQHHQKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinghui Chen, Vasant G. Honavar, Yuanpu Cao, Zehao Liu","submitted_at":"2026-05-26T23:30:01Z","abstract_excerpt":"Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO, however, whose group-relative advantage naturally concentrates learning on a sweet spot of intermediate-difficulty questions, SDPO's KL-based advantage lacks an implicit notion of difficulty awareness.\n  We analyze this gap through the lens of GRPO's advantage normalization. Extending the learnability framework to normalized rewards, we show that normalizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27765","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/2605.27765/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":"2026-05-28T01:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"krizCn2Ft6GB6NBqtp0KRce1pG0x0fUcjmjhaJ4ARnqpq7ObIik3Ci10GQ1/xCOvtOrv/bMoONKm9FRhBjc9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:19:30.956724Z"},"content_sha256":"f9bef46d5a0674c82682660a2aa64080bbe87e4fb3ec026d6cedc9cbd9b8a32c","schema_version":"1.0","event_id":"sha256:f9bef46d5a0674c82682660a2aa64080bbe87e4fb3ec026d6cedc9cbd9b8a32c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ/bundle.json","state_url":"https://pith.science/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ/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":"2026-05-30T12:19:30Z","links":{"resolver":"https://pith.science/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ","bundle":"https://pith.science/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ/bundle.json","state":"https://pith.science/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJLEFONXJJRN5SP7FUQYQHHQKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CJLEFONXJJRN5SP7FUQYQHHQKJ","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":"ceaee9abbb9eb708eb48f6f0ebcb14da28ec4d801a3bfce02ffbfb4982ed5c7c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T23:30:01Z","title_canon_sha256":"823ce2018611d67546e1d93952525598a6d42498403957450540e0294d2221df"},"schema_version":"1.0","source":{"id":"2605.27765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27765","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27765v1","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27765","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"CJLEFONXJJRN","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"CJLEFONXJJRN5SP7","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"CJLEFONX","created_at":"2026-05-28T01:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:f9bef46d5a0674c82682660a2aa64080bbe87e4fb3ec026d6cedc9cbd9b8a32c","target":"graph","created_at":"2026-05-28T01:04:48Z","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/2605.27765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO, however, whose group-relative advantage naturally concentrates learning on a sweet spot of intermediate-difficulty questions, SDPO's KL-based advantage lacks an implicit notion of difficulty awareness.\n  We analyze this gap through the lens of GRPO's advantage normalization. Extending the learnability framework to normalized rewards, we show that normalizatio","authors_text":"Jinghui Chen, Vasant G. Honavar, Yuanpu Cao, Zehao Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T23:30:01Z","title":"Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27765","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":"sha256:0a6df0a77bdf8768e76ac77e6005c0ca629b6235e743ccc23f4e04b46239256e","target":"record","created_at":"2026-05-28T01:04:48Z","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":"ceaee9abbb9eb708eb48f6f0ebcb14da28ec4d801a3bfce02ffbfb4982ed5c7c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T23:30:01Z","title_canon_sha256":"823ce2018611d67546e1d93952525598a6d42498403957450540e0294d2221df"},"schema_version":"1.0","source":{"id":"2605.27765","kind":"arxiv","version":1}},"canonical_sha256":"125642b9b74a62dec9ff2d21881cf0527094bc652a5ae4f925e300ec7387f9a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"125642b9b74a62dec9ff2d21881cf0527094bc652a5ae4f925e300ec7387f9a6","first_computed_at":"2026-05-28T01:04:48.330348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:48.330348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54aT5sZuSYZrGl4JwoZSoaqP7kRkKcUtNqksz76RN/rellDwg3r6SPUYV316n1ax5TWMerT9CiY1QDIqKUj5Cg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:48.330729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a6df0a77bdf8768e76ac77e6005c0ca629b6235e743ccc23f4e04b46239256e","sha256:f9bef46d5a0674c82682660a2aa64080bbe87e4fb3ec026d6cedc9cbd9b8a32c"],"state_sha256":"10032c9155696d3f9c81c03953d873bac8b4b46bf3bce4f1c02e66442bce0725"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8nWX7up9OV25uGKXTqKPaypz0eGuF9RH4cbctuSYaRfd1XgUv0UOU2romfJ1TfCccOv2oS0lzuccXN59oo/LBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:19:30.959692Z","bundle_sha256":"a001ef8e27298b6a88b3ce1ce8e0d945263a3dbd7df46d7ffec1e69d3c88cb1b"}}