{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CNVG4DOPIRUAT3Y773JHFBWN6U","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":"55b4ab426dc40886d18c94f1e5c8bafb93b2984caff4741192473df0169a429e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T12:59:10Z","title_canon_sha256":"ec4fcaa8b852c6f5818a742b5d96b1464b32448b2038821f6b2e5d09da9a805b"},"schema_version":"1.0","source":{"id":"2608.04794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04794","created_at":"2026-08-06T01:47:07Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04794v1","created_at":"2026-08-06T01:47:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04794","created_at":"2026-08-06T01:47:07Z"},{"alias_kind":"pith_short_12","alias_value":"CNVG4DOPIRUA","created_at":"2026-08-06T01:47:07Z"},{"alias_kind":"pith_short_16","alias_value":"CNVG4DOPIRUAT3Y7","created_at":"2026-08-06T01:47:07Z"},{"alias_kind":"pith_short_8","alias_value":"CNVG4DOP","created_at":"2026-08-06T01:47:07Z"}],"graph_snapshots":[{"event_id":"sha256:848b31a58720dcae596c38965a02cab02111ef3678bfc2c8ad13bdf72e0d729b","target":"graph","created_at":"2026-08-06T01:47:07Z","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/2608.04794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it. Reported gains, however, come almost exclusively from narrow, low-difficulty settings, leaving open a basic question: as a lone objective, with no reward term, does SD teach anything? We reproduce SDPO's reported gains in its easy setting, then apply the identical setup to difficult tasks and find that","authors_text":"Ahmed Awadallah, Akshay Nambi, Chinmay Karkar, Sarthak Harne, Yash Pandya","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T12:59:10Z","title":"Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04794","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":"sha256:7e142308b5a761c39a57a778102359e4b4992d8e9650a40e3dc9dec9c6c1cba3","target":"record","created_at":"2026-08-06T01:47:07Z","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":"55b4ab426dc40886d18c94f1e5c8bafb93b2984caff4741192473df0169a429e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T12:59:10Z","title_canon_sha256":"ec4fcaa8b852c6f5818a742b5d96b1464b32448b2038821f6b2e5d09da9a805b"},"schema_version":"1.0","source":{"id":"2608.04794","kind":"arxiv","version":1}},"canonical_sha256":"136a6e0dcf446809ef1ffed27286cdf50d1a348366dde8ab13c4bfd33dfa25ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"136a6e0dcf446809ef1ffed27286cdf50d1a348366dde8ab13c4bfd33dfa25ad","first_computed_at":"2026-08-06T01:47:07.578444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:47:07.578444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GyLM2Rn1npBF5or+gvk3tbdbufVYfxc59OzNg7zcvCoiQbIyXVB3C6+rNM2seScW/KQS1TSoqP14oBZfZVP5CQ==","signature_status":"signed_v1","signed_at":"2026-08-06T01:47:07.579862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e142308b5a761c39a57a778102359e4b4992d8e9650a40e3dc9dec9c6c1cba3","sha256:848b31a58720dcae596c38965a02cab02111ef3678bfc2c8ad13bdf72e0d729b"],"state_sha256":"e98b087c9c3a9a7febb42a4489f07c8be5f05bbce88075aea1928af0ddd0baa4"}