{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XST5JYQVSI4FPDLYXGWK54TIZM","short_pith_number":"pith:XST5JYQV","canonical_record":{"source":{"id":"2606.12507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"b44b4bff8a37f604baa7e3c3d717995ff2c96f56618893e4c78ab93912169728","abstract_canon_sha256":"c01b6e96176d37d5b3badd0383b386456a1845e089f41653ac6a98c63b6a525e"},"schema_version":"1.0"},"canonical_sha256":"bca7d4e2159238578d78b9acaef268cb0e75df3e4af423f0efc36263586f9382","source":{"kind":"arxiv","id":"2606.12507","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12507","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12507v1","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12507","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"XST5JYQVSI4F","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"pith_short_16","alias_value":"XST5JYQVSI4FPDLY","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"pith_short_8","alias_value":"XST5JYQV","created_at":"2026-06-12T00:07:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XST5JYQVSI4FPDLYXGWK54TIZM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.12507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"b44b4bff8a37f604baa7e3c3d717995ff2c96f56618893e4c78ab93912169728","abstract_canon_sha256":"c01b6e96176d37d5b3badd0383b386456a1845e089f41653ac6a98c63b6a525e"},"schema_version":"1.0"},"canonical_sha256":"bca7d4e2159238578d78b9acaef268cb0e75df3e4af423f0efc36263586f9382","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:52.785569Z","signature_b64":"g+iEmUzkFFm9oyHTiX5Ary7xaMWUKWrmRapLGgy4spBCEsZLJTSCfyUIFwLqinXl2yajUJG0KzrCLX/zVRyCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bca7d4e2159238578d78b9acaef268cb0e75df3e4af423f0efc36263586f9382","last_reissued_at":"2026-06-12T00:07:52.785145Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:52.785145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.12507","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":"2026-06-12T00:07:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGmvKgTWKdXuBAH34pEnrxguSPnHrgUNnQqcyIWWMIt3VcSkg5gWlCjbu+R2l5RmsxjVYu24YK5iBeZKJeesDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:31:57.149738Z"},"content_sha256":"52f56672f05804a33e6415d3742c53136dfe89f14de709e99a1a03a3155202eb","schema_version":"1.0","event_id":"sha256:52f56672f05804a33e6415d3742c53136dfe89f14de709e99a1a03a3155202eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XST5JYQVSI4FPDLYXGWK54TIZM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aakash Sabharwal, Advait Gosai, Anas Mahmoud, Bing Liu, MohammadHossein Rezaei, Razvan-Gabriel Dumitru, Utkarsh Tyagi, Yunzhong He, Zihao Wang","submitted_at":"2026-06-10T17:53:19Z","abstract_excerpt":"Rubrics have emerged as an alternative to RLVR in open-ended domains where a single ground-truth final answer is not available. Existing rubric-based training methods rely on an LLM verifier that scores each rollout against rubrics. This introduces substantial training-time overhead, exposes optimization to verifier-specific biases, and reduces rubric feedback to a sparse end-of-trajectory signal. We propose Rubric-Guided Self-Distillation (RGSD), a verifier-free training method in which the base policy, conditioned on the rubric, serves as the teacher for the unconditioned student. RGSD disti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12507","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/2606.12507/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":"2026-06-12T00:07:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D4uwVzKVOugFGbh7O+z0M8saS0s2g8yHGvXMMHFyxkbUOqkvQsncv/UJLugzMo4Pp2T3LFgQUIMZ8HyYZfA/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T08:31:57.150207Z"},"content_sha256":"d6abc965f410e904a597816258f5861a1aa01d0641e7c08af4851325f5d34514","schema_version":"1.0","event_id":"sha256:d6abc965f410e904a597816258f5861a1aa01d0641e7c08af4851325f5d34514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XST5JYQVSI4FPDLYXGWK54TIZM/bundle.json","state_url":"https://pith.science/pith/XST5JYQVSI4FPDLYXGWK54TIZM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XST5JYQVSI4FPDLYXGWK54TIZM/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":"2026-07-01T08:31:57Z","links":{"resolver":"https://pith.science/pith/XST5JYQVSI4FPDLYXGWK54TIZM","bundle":"https://pith.science/pith/XST5JYQVSI4FPDLYXGWK54TIZM/bundle.json","state":"https://pith.science/pith/XST5JYQVSI4FPDLYXGWK54TIZM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XST5JYQVSI4FPDLYXGWK54TIZM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XST5JYQVSI4FPDLYXGWK54TIZM","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":"c01b6e96176d37d5b3badd0383b386456a1845e089f41653ac6a98c63b6a525e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:53:19Z","title_canon_sha256":"b44b4bff8a37f604baa7e3c3d717995ff2c96f56618893e4c78ab93912169728"},"schema_version":"1.0","source":{"id":"2606.12507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12507","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12507v1","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12507","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"XST5JYQVSI4F","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"pith_short_16","alias_value":"XST5JYQVSI4FPDLY","created_at":"2026-06-12T00:07:52Z"},{"alias_kind":"pith_short_8","alias_value":"XST5JYQV","created_at":"2026-06-12T00:07:52Z"}],"graph_snapshots":[{"event_id":"sha256:d6abc965f410e904a597816258f5861a1aa01d0641e7c08af4851325f5d34514","target":"graph","created_at":"2026-06-12T00:07:52Z","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/2606.12507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubrics have emerged as an alternative to RLVR in open-ended domains where a single ground-truth final answer is not available. Existing rubric-based training methods rely on an LLM verifier that scores each rollout against rubrics. This introduces substantial training-time overhead, exposes optimization to verifier-specific biases, and reduces rubric feedback to a sparse end-of-trajectory signal. We propose Rubric-Guided Self-Distillation (RGSD), a verifier-free training method in which the base policy, conditioned on the rubric, serves as the teacher for the unconditioned student. RGSD disti","authors_text":"Aakash Sabharwal, Advait Gosai, Anas Mahmoud, Bing Liu, MohammadHossein Rezaei, Razvan-Gabriel Dumitru, Utkarsh Tyagi, Yunzhong He, Zihao Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:53:19Z","title":"Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12507","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":"sha256:52f56672f05804a33e6415d3742c53136dfe89f14de709e99a1a03a3155202eb","target":"record","created_at":"2026-06-12T00:07:52Z","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":"c01b6e96176d37d5b3badd0383b386456a1845e089f41653ac6a98c63b6a525e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:53:19Z","title_canon_sha256":"b44b4bff8a37f604baa7e3c3d717995ff2c96f56618893e4c78ab93912169728"},"schema_version":"1.0","source":{"id":"2606.12507","kind":"arxiv","version":1}},"canonical_sha256":"bca7d4e2159238578d78b9acaef268cb0e75df3e4af423f0efc36263586f9382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bca7d4e2159238578d78b9acaef268cb0e75df3e4af423f0efc36263586f9382","first_computed_at":"2026-06-12T00:07:52.785145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T00:07:52.785145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g+iEmUzkFFm9oyHTiX5Ary7xaMWUKWrmRapLGgy4spBCEsZLJTSCfyUIFwLqinXl2yajUJG0KzrCLX/zVRyCBg==","signature_status":"signed_v1","signed_at":"2026-06-12T00:07:52.785569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52f56672f05804a33e6415d3742c53136dfe89f14de709e99a1a03a3155202eb","sha256:d6abc965f410e904a597816258f5861a1aa01d0641e7c08af4851325f5d34514"],"state_sha256":"2e7cc1e63f15d3d751c92beb849106a9d8c2b999ed372b123a2777dc4a714d33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7N61sNhr6RNfZV4sr/F/Abr1LDhNpiDyFBb7uxmN0nEQhVtHwgU5SkpW15RIv+Sa1ZVnRv20s9n5i8kaPCKTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T08:31:57.152707Z","bundle_sha256":"44198700cad43c043543950c27a01e2d2c1cf9e163af0e0a942bd8f536375dc5"}}