{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4GGJLRX2LNUQT7S6MXO656EMAG","short_pith_number":"pith:4GGJLRX2","canonical_record":{"source":{"id":"2606.07040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T08:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"1da676430a654eb0bff2255673c4253f2b91d24675b19390a19e5b7d40fb2077","abstract_canon_sha256":"f3c6d12122953512d9882ff554ba5c54b502e3d7241826dffbda946a89bc03a6"},"schema_version":"1.0"},"canonical_sha256":"e18c95c6fa5b6909fe5e65ddeef88c0186fc770630dc8d1654e994cf4a4cec35","source":{"kind":"arxiv","id":"2606.07040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07040","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07040v1","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07040","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"4GGJLRX2LNUQ","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"4GGJLRX2LNUQT7S6","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"4GGJLRX2","created_at":"2026-06-08T01:04:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4GGJLRX2LNUQT7S6MXO656EMAG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T08:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"1da676430a654eb0bff2255673c4253f2b91d24675b19390a19e5b7d40fb2077","abstract_canon_sha256":"f3c6d12122953512d9882ff554ba5c54b502e3d7241826dffbda946a89bc03a6"},"schema_version":"1.0"},"canonical_sha256":"e18c95c6fa5b6909fe5e65ddeef88c0186fc770630dc8d1654e994cf4a4cec35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:42.861023Z","signature_b64":"GuPVx06EMOh8lyKvM/b90U1kSF7s79b1B4HTzsOvofx/pEE/KOX365Ns46mebK//TfzUESj5fkVz+s0ZLr+fAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e18c95c6fa5b6909fe5e65ddeef88c0186fc770630dc8d1654e994cf4a4cec35","last_reissued_at":"2026-06-08T01:04:42.860273Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:42.860273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07040","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":"2026-06-08T01:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qN6kq2l0i6dxVWR09HULLherBU01x/anTV6Z/5ExPHwai2fhgv3sfGQQd7pfo6UdPCL4mQ0IDYmoHgMlFnO/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T17:52:33.038832Z"},"content_sha256":"8f23e3aa4ed3d0003016b2dff9604f7cf22e4e65d4e285df643f5b267637f749","schema_version":"1.0","event_id":"sha256:8f23e3aa4ed3d0003016b2dff9604f7cf22e4e65d4e285df643f5b267637f749"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4GGJLRX2LNUQT7S6MXO656EMAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daoxin Zhang, Linjuan Wu, Weiming Lu, Xing Yue, Yongliang Shen","submitted_at":"2026-06-05T08:34:06Z","abstract_excerpt":"Open-ended reward modeling requires judges that can follow subtle, domain-specific preferences when verifiable answers are unavailable. Existing rubric-based methods often address this by generating criteria online for each query, but the extra generation step can add inference overhead and produce rigid or misaligned guidance. We introduce Eval-Skill, an exploration-guided method that synthesizes reusable evaluation skills for reward modeling and reframes reward guidance as context evolution rather than parameter training or per-query rubric generation. Using only 100 cases per domain for ski"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07040","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/2606.07040/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":"2026-06-08T01:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uIJf/d7UuxdF8ThzP+6CLtNCewgMPtBP28iRmk58gIxjVAEKVHAVxk8QJk/uP7JWOqhRZH/GoyMPKwG4P3UbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T17:52:33.039217Z"},"content_sha256":"9080f2b67560b5da0956c1c2b99f8988cea6433cad31ea484458f22d96ad17e1","schema_version":"1.0","event_id":"sha256:9080f2b67560b5da0956c1c2b99f8988cea6433cad31ea484458f22d96ad17e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4GGJLRX2LNUQT7S6MXO656EMAG/bundle.json","state_url":"https://pith.science/pith/4GGJLRX2LNUQT7S6MXO656EMAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4GGJLRX2LNUQT7S6MXO656EMAG/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":"2026-07-02T17:52:33Z","links":{"resolver":"https://pith.science/pith/4GGJLRX2LNUQT7S6MXO656EMAG","bundle":"https://pith.science/pith/4GGJLRX2LNUQT7S6MXO656EMAG/bundle.json","state":"https://pith.science/pith/4GGJLRX2LNUQT7S6MXO656EMAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4GGJLRX2LNUQT7S6MXO656EMAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4GGJLRX2LNUQT7S6MXO656EMAG","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":"f3c6d12122953512d9882ff554ba5c54b502e3d7241826dffbda946a89bc03a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T08:34:06Z","title_canon_sha256":"1da676430a654eb0bff2255673c4253f2b91d24675b19390a19e5b7d40fb2077"},"schema_version":"1.0","source":{"id":"2606.07040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07040","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07040v1","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07040","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"4GGJLRX2LNUQ","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"4GGJLRX2LNUQT7S6","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"4GGJLRX2","created_at":"2026-06-08T01:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:9080f2b67560b5da0956c1c2b99f8988cea6433cad31ea484458f22d96ad17e1","target":"graph","created_at":"2026-06-08T01:04:42Z","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/2606.07040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-ended reward modeling requires judges that can follow subtle, domain-specific preferences when verifiable answers are unavailable. Existing rubric-based methods often address this by generating criteria online for each query, but the extra generation step can add inference overhead and produce rigid or misaligned guidance. We introduce Eval-Skill, an exploration-guided method that synthesizes reusable evaluation skills for reward modeling and reframes reward guidance as context evolution rather than parameter training or per-query rubric generation. Using only 100 cases per domain for ski","authors_text":"Daoxin Zhang, Linjuan Wu, Weiming Lu, Xing Yue, Yongliang Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T08:34:06Z","title":"Beyond Rubrics: Exploration-Guided Evaluation Skills for Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07040","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":"sha256:8f23e3aa4ed3d0003016b2dff9604f7cf22e4e65d4e285df643f5b267637f749","target":"record","created_at":"2026-06-08T01:04:42Z","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":"f3c6d12122953512d9882ff554ba5c54b502e3d7241826dffbda946a89bc03a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T08:34:06Z","title_canon_sha256":"1da676430a654eb0bff2255673c4253f2b91d24675b19390a19e5b7d40fb2077"},"schema_version":"1.0","source":{"id":"2606.07040","kind":"arxiv","version":1}},"canonical_sha256":"e18c95c6fa5b6909fe5e65ddeef88c0186fc770630dc8d1654e994cf4a4cec35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e18c95c6fa5b6909fe5e65ddeef88c0186fc770630dc8d1654e994cf4a4cec35","first_computed_at":"2026-06-08T01:04:42.860273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:42.860273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GuPVx06EMOh8lyKvM/b90U1kSF7s79b1B4HTzsOvofx/pEE/KOX365Ns46mebK//TfzUESj5fkVz+s0ZLr+fAw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:42.861023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f23e3aa4ed3d0003016b2dff9604f7cf22e4e65d4e285df643f5b267637f749","sha256:9080f2b67560b5da0956c1c2b99f8988cea6433cad31ea484458f22d96ad17e1"],"state_sha256":"2ad16f42b8d2b91bde8693e5545a1dbf866b7faaeb7f12e1c3d022ed0673ebe2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ff6ZEkcrLIcPAT4JBO/pzeTKhBlwIwQfreOKOWZTRkwrqMrpyZ2RVcWcR5tEjl1s72RXb6/s0ezw6eMB+cmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T17:52:33.041525Z","bundle_sha256":"841b26dab4f65273ccf6844b97e65dad6ad3508d45e0b0e10019e9918535c38a"}}