{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6DYYGLOPUVS6WSZI3CFR4IC2A2","short_pith_number":"pith:6DYYGLOP","canonical_record":{"source":{"id":"2607.04412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T17:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"0b3a136d0f1c63fbcbc379c20e466bf183c10ade4a3d0dd4223d79f35ef14fb9","abstract_canon_sha256":"053bd6bb5176b50dc7b803a624892b3e70b9666d5240b860e21d25863014cd17"},"schema_version":"1.0"},"canonical_sha256":"f0f1832dcfa565eb4b28d88b1e205a0693f2a7aadda559ac49dbdda15bfcaee3","source":{"kind":"arxiv","id":"2607.04412","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04412","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04412v1","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04412","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"pith_short_12","alias_value":"6DYYGLOPUVS6","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"pith_short_16","alias_value":"6DYYGLOPUVS6WSZI","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"pith_short_8","alias_value":"6DYYGLOP","created_at":"2026-07-07T02:19:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6DYYGLOPUVS6WSZI3CFR4IC2A2","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T17:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"0b3a136d0f1c63fbcbc379c20e466bf183c10ade4a3d0dd4223d79f35ef14fb9","abstract_canon_sha256":"053bd6bb5176b50dc7b803a624892b3e70b9666d5240b860e21d25863014cd17"},"schema_version":"1.0"},"canonical_sha256":"f0f1832dcfa565eb4b28d88b1e205a0693f2a7aadda559ac49dbdda15bfcaee3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:17.277370Z","signature_b64":"aLVidL8y1tptijumAzYDs8aP5g8KlQ8jc8yOeL/ZQ7hG/H1vSQ+PSraFTPNdr2xjJ1Jga1b/PSsauOMrcjvtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f1832dcfa565eb4b28d88b1e205a0693f2a7aadda559ac49dbdda15bfcaee3","last_reissued_at":"2026-07-07T02:19:17.276620Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:17.276620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04412","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":"2026-07-07T02:19:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nC1599qhIzM9AhfR6/s9q3iC9tRmGcZRTwI5fYXIxCQhyuVv8f8FDl2pY8TnwvhYRhiuMCBWVkV02mFsyhAyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:10:40.282388Z"},"content_sha256":"982d87e31979a71277c579a3b7d4bc521f3e12d9159099d51477f452a7caf202","schema_version":"1.0","event_id":"sha256:982d87e31979a71277c579a3b7d4bc521f3e12d9159099d51477f452a7caf202"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6DYYGLOPUVS6WSZI3CFR4IC2A2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hwanjun Song, Jaehun Jung, Joonkee Kim, Namgyu Ho, Sangmin Bae, Sangmin Hwang, Seungone Kim, Se-Young Yun, Yongjin Yang, Yujin Kim","submitted_at":"2026-07-05T17:05:13Z","abstract_excerpt":"Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static, drawn from fixed corpora. This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal when prompts fail to elicit quality variance among rollouts. To address this misalignment, we introduce LLM-as-a-Tuto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04412","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/2607.04412/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":"2026-07-07T02:19:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OgqsnTIoggx6N1eUPFHn8N3i5IMECQB1SZLnTphipnTn4DoLX/36MCUP2qe8Ja1x/ECJ7LdPzAgFI3zQgmiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:10:40.282895Z"},"content_sha256":"5b75e0d60a10521a5bba9f25262beae835467c5318fa86220b4079377c9442d8","schema_version":"1.0","event_id":"sha256:5b75e0d60a10521a5bba9f25262beae835467c5318fa86220b4079377c9442d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2/bundle.json","state_url":"https://pith.science/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2/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":"2026-08-05T08:10:40Z","links":{"resolver":"https://pith.science/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2","bundle":"https://pith.science/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2/bundle.json","state":"https://pith.science/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DYYGLOPUVS6WSZI3CFR4IC2A2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6DYYGLOPUVS6WSZI3CFR4IC2A2","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":"053bd6bb5176b50dc7b803a624892b3e70b9666d5240b860e21d25863014cd17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T17:05:13Z","title_canon_sha256":"0b3a136d0f1c63fbcbc379c20e466bf183c10ade4a3d0dd4223d79f35ef14fb9"},"schema_version":"1.0","source":{"id":"2607.04412","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04412","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04412v1","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04412","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"pith_short_12","alias_value":"6DYYGLOPUVS6","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"pith_short_16","alias_value":"6DYYGLOPUVS6WSZI","created_at":"2026-07-07T02:19:17Z"},{"alias_kind":"pith_short_8","alias_value":"6DYYGLOP","created_at":"2026-07-07T02:19:17Z"}],"graph_snapshots":[{"event_id":"sha256:5b75e0d60a10521a5bba9f25262beae835467c5318fa86220b4079377c9442d8","target":"graph","created_at":"2026-07-07T02:19:17Z","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/2607.04412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static, drawn from fixed corpora. This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal when prompts fail to elicit quality variance among rollouts. To address this misalignment, we introduce LLM-as-a-Tuto","authors_text":"Hwanjun Song, Jaehun Jung, Joonkee Kim, Namgyu Ho, Sangmin Bae, Sangmin Hwang, Seungone Kim, Se-Young Yun, Yongjin Yang, Yujin Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T17:05:13Z","title":"LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04412","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":"sha256:982d87e31979a71277c579a3b7d4bc521f3e12d9159099d51477f452a7caf202","target":"record","created_at":"2026-07-07T02:19:17Z","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":"053bd6bb5176b50dc7b803a624892b3e70b9666d5240b860e21d25863014cd17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-05T17:05:13Z","title_canon_sha256":"0b3a136d0f1c63fbcbc379c20e466bf183c10ade4a3d0dd4223d79f35ef14fb9"},"schema_version":"1.0","source":{"id":"2607.04412","kind":"arxiv","version":1}},"canonical_sha256":"f0f1832dcfa565eb4b28d88b1e205a0693f2a7aadda559ac49dbdda15bfcaee3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0f1832dcfa565eb4b28d88b1e205a0693f2a7aadda559ac49dbdda15bfcaee3","first_computed_at":"2026-07-07T02:19:17.276620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:17.276620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aLVidL8y1tptijumAzYDs8aP5g8KlQ8jc8yOeL/ZQ7hG/H1vSQ+PSraFTPNdr2xjJ1Jga1b/PSsauOMrcjvtDg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:17.277370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04412","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:982d87e31979a71277c579a3b7d4bc521f3e12d9159099d51477f452a7caf202","sha256:5b75e0d60a10521a5bba9f25262beae835467c5318fa86220b4079377c9442d8"],"state_sha256":"96390c96427e7d432b018acd76836fc2b0ec00d9f141c6ab941d99b1e18e8cc4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wErl0ZCp36PZcHkjHI/L+rYncEjFzwvT8HjNnzq8yPCZ7A9HGiCAzgxIrbtQ476hvZEq9Zv3uTuCuKPl8QCVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:10:40.287784Z","bundle_sha256":"5f3ee81befd431ba775d96cdadc9a6f82594df01d7e6fb9591df8849c8d82a0f"}}