{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AEF36MJKZKRGRBKOZQFYAPVQCX","short_pith_number":"pith:AEF36MJK","canonical_record":{"source":{"id":"2605.26184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:52:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84f5e5ca5db5e09e4916b7ad6f469dc1e97dd9a371a1e2e04b04ad130c610edf","abstract_canon_sha256":"f9e93b1cde6f93ba252d87c6407e9dcf44983e6e23163c90a6855cc951c1c4a2"},"schema_version":"1.0"},"canonical_sha256":"010bbf312acaa268854ecc0b803eb015c519a67eab759193ee1ca36d8665145b","source":{"kind":"arxiv","id":"2605.26184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26184","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26184v1","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26184","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"AEF36MJKZKRG","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"AEF36MJKZKRGRBKO","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"AEF36MJK","created_at":"2026-05-27T00:04:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AEF36MJKZKRGRBKOZQFYAPVQCX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:52:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84f5e5ca5db5e09e4916b7ad6f469dc1e97dd9a371a1e2e04b04ad130c610edf","abstract_canon_sha256":"f9e93b1cde6f93ba252d87c6407e9dcf44983e6e23163c90a6855cc951c1c4a2"},"schema_version":"1.0"},"canonical_sha256":"010bbf312acaa268854ecc0b803eb015c519a67eab759193ee1ca36d8665145b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T00:04:27.803338Z","signature_b64":"ELd+PzcaYBaxzTcZiQr7EYr27ZWoAQNrZshUG0whTqA/6v6Ekusw8nvwfaOy7xffrBfFFwSwYCracciZuWGKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"010bbf312acaa268854ecc0b803eb015c519a67eab759193ee1ca36d8665145b","last_reissued_at":"2026-05-27T00:04:27.802643Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T00:04:27.802643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26184","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":"2026-05-27T00:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GzEvz0TWb1urPemasS9vH2tRwewrM8StD3O0RQ0Nl+f6+YFKAubpcTAITGw6wjoAeAfZo4DvhQKFnZ6KoV3cDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:07:38.100431Z"},"content_sha256":"38ab1c45365dbd33cdacb9ec9e9c5fb132f730d81e83632271e81cfe78c8b4ab","schema_version":"1.0","event_id":"sha256:38ab1c45365dbd33cdacb9ec9e9c5fb132f730d81e83632271e81cfe78c8b4ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AEF36MJKZKRGRBKOZQFYAPVQCX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Li Song, Wei Liu, Yuelin Hu, Zhenbo Yu, Zhengxue Cheng","submitted_at":"2026-05-25T07:52:29Z","abstract_excerpt":"Hybrid post-training usually combines supervised fine-tuning and reinforcement learning, but fixed mixing schedules cannot adapt when the relative noise of the two signals changes over time. We propose GAC, a noise-aware controller that derives an adaptive mixing weight from online estimates of gradient variance and disagreement between the two training signals. The method adds smoothing, prior guidance, and bounded updates while reusing existing training tensors. Experiments on math, code, science, and logic benchmarks show that GAC consistently improves hybrid post-training over strong fixed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26184","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/2605.26184/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":"2026-05-27T00:04:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7lv2K0zkvO7+TnNSTIQz/LGTXdR4kTsrFbXKvTCo8Fq7OO8ka4hyIBt+BigVd5Z5fh+mDyrU+Zo6HaAI8J5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:07:38.100822Z"},"content_sha256":"f6a78ba2f37a7268946ce381139ff61a8295c381157823402502439e815a0091","schema_version":"1.0","event_id":"sha256:f6a78ba2f37a7268946ce381139ff61a8295c381157823402502439e815a0091"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEF36MJKZKRGRBKOZQFYAPVQCX/bundle.json","state_url":"https://pith.science/pith/AEF36MJKZKRGRBKOZQFYAPVQCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEF36MJKZKRGRBKOZQFYAPVQCX/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":"2026-05-30T11:07:38Z","links":{"resolver":"https://pith.science/pith/AEF36MJKZKRGRBKOZQFYAPVQCX","bundle":"https://pith.science/pith/AEF36MJKZKRGRBKOZQFYAPVQCX/bundle.json","state":"https://pith.science/pith/AEF36MJKZKRGRBKOZQFYAPVQCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEF36MJKZKRGRBKOZQFYAPVQCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AEF36MJKZKRGRBKOZQFYAPVQCX","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":"f9e93b1cde6f93ba252d87c6407e9dcf44983e6e23163c90a6855cc951c1c4a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:52:29Z","title_canon_sha256":"84f5e5ca5db5e09e4916b7ad6f469dc1e97dd9a371a1e2e04b04ad130c610edf"},"schema_version":"1.0","source":{"id":"2605.26184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26184","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26184v1","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26184","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_12","alias_value":"AEF36MJKZKRG","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_16","alias_value":"AEF36MJKZKRGRBKO","created_at":"2026-05-27T00:04:27Z"},{"alias_kind":"pith_short_8","alias_value":"AEF36MJK","created_at":"2026-05-27T00:04:27Z"}],"graph_snapshots":[{"event_id":"sha256:f6a78ba2f37a7268946ce381139ff61a8295c381157823402502439e815a0091","target":"graph","created_at":"2026-05-27T00:04:27Z","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/2605.26184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hybrid post-training usually combines supervised fine-tuning and reinforcement learning, but fixed mixing schedules cannot adapt when the relative noise of the two signals changes over time. We propose GAC, a noise-aware controller that derives an adaptive mixing weight from online estimates of gradient variance and disagreement between the two training signals. The method adds smoothing, prior guidance, and bounded updates while reusing existing training tensors. Experiments on math, code, science, and logic benchmarks show that GAC consistently improves hybrid post-training over strong fixed","authors_text":"Li Song, Wei Liu, Yuelin Hu, Zhenbo Yu, Zhengxue Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:52:29Z","title":"GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26184","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":"sha256:38ab1c45365dbd33cdacb9ec9e9c5fb132f730d81e83632271e81cfe78c8b4ab","target":"record","created_at":"2026-05-27T00:04:27Z","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":"f9e93b1cde6f93ba252d87c6407e9dcf44983e6e23163c90a6855cc951c1c4a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:52:29Z","title_canon_sha256":"84f5e5ca5db5e09e4916b7ad6f469dc1e97dd9a371a1e2e04b04ad130c610edf"},"schema_version":"1.0","source":{"id":"2605.26184","kind":"arxiv","version":1}},"canonical_sha256":"010bbf312acaa268854ecc0b803eb015c519a67eab759193ee1ca36d8665145b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"010bbf312acaa268854ecc0b803eb015c519a67eab759193ee1ca36d8665145b","first_computed_at":"2026-05-27T00:04:27.802643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T00:04:27.802643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ELd+PzcaYBaxzTcZiQr7EYr27ZWoAQNrZshUG0whTqA/6v6Ekusw8nvwfaOy7xffrBfFFwSwYCracciZuWGKAA==","signature_status":"signed_v1","signed_at":"2026-05-27T00:04:27.803338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38ab1c45365dbd33cdacb9ec9e9c5fb132f730d81e83632271e81cfe78c8b4ab","sha256:f6a78ba2f37a7268946ce381139ff61a8295c381157823402502439e815a0091"],"state_sha256":"2f908c953892ef8a24a2306130a3617d27e04ea510d5207df3dea0446e8e7569"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yxh/A4tUApxQ6n2KSks59Q5r0FXWgVVuAdz02XRrNNXuf/qVUE3y6RncuPMdbhJx1dMwmeDYLZA0BC6GN3HXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:07:38.103216Z","bundle_sha256":"fcd5d82f97c49d15c4676a0b7f414068137e2691a8722445f31145d8c2e3e688"}}