{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DIZ3IBNGIF2G2ZPXB2FQ6IDDOI","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":"16ec8601d10f009d9248114f609965cbba09947f83f57b1702ef7ddf4c143b38","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T06:02:15Z","title_canon_sha256":"6983faec42c25a46996143375fc89e86dbf50af4277b57727ce7cab6f70a3d5c"},"schema_version":"1.0","source":{"id":"2606.07520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07520","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07520v1","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07520","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"DIZ3IBNGIF2G","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"DIZ3IBNGIF2G2ZPX","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"DIZ3IBNG","created_at":"2026-06-09T00:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:3b9a99aa9b289b2f8cb0ced1d82e8e904780070465b18dd57d30e074a7bd0de0","target":"graph","created_at":"2026-06-09T00:04:41Z","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/2606.07520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.g., output length) to unverifiable ones (e.g., tone). Reinforcement learning with verifiable rewards has emerged as a paradigm for IF tasks, leveraging LLM-as-a-judge to assess unverifiable constraints. However, we empirically find that this approach remains a significant bottleneck, suffering from severe reward hacking and higher computational overhead. In this work, we first analyze the generalization capabilities of unverifiable constraints and discover","authors_text":"Bibo Cai, Dandan Tu, Haonan Song, Qixun Zhang, Ting Liu, Wu Ning, Xiao Ding, Yirong Zeng, Yufei Liu, Yutai Hou, Yuxiang He, Yuxian Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T06:02:15Z","title":"TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07520","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:f706f66f63dc0646961938b8eea6e759350ccd52d03acb86bacb0e4e09b1f735","target":"record","created_at":"2026-06-09T00:04:41Z","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":"16ec8601d10f009d9248114f609965cbba09947f83f57b1702ef7ddf4c143b38","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-19T06:02:15Z","title_canon_sha256":"6983faec42c25a46996143375fc89e86dbf50af4277b57727ce7cab6f70a3d5c"},"schema_version":"1.0","source":{"id":"2606.07520","kind":"arxiv","version":1}},"canonical_sha256":"1a33b405a641746d65f70e8b0f2063720362a63041f8816053880526e2ca9c47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a33b405a641746d65f70e8b0f2063720362a63041f8816053880526e2ca9c47","first_computed_at":"2026-06-09T00:04:41.281436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:41.281436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uSgel6RNQn9UTIiFJxdxXXClftxqm5EdkEPZJRomXfN0s8Mgz5Ix+HPrjGElHzOPikQo5owoSLWoz/4oXGdCDw==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:41.282251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f706f66f63dc0646961938b8eea6e759350ccd52d03acb86bacb0e4e09b1f735","sha256:3b9a99aa9b289b2f8cb0ced1d82e8e904780070465b18dd57d30e074a7bd0de0"],"state_sha256":"b84010548edfb76cd7e9cece5d7667741941bfeaa647123e383f73e53cf3c4bc"}