{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AE7JSO7US72GWJ25YRVKSPVFZ3","short_pith_number":"pith:AE7JSO7U","canonical_record":{"source":{"id":"2607.05184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:01:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ad7b4aa4741bf92f39ee5bfd602b38849959b2837198d8d8f8e350e2681e2e2","abstract_canon_sha256":"b594c79ff4302318796e721da7d981906d385c93345b85f7f8356877b209fec2"},"schema_version":"1.0"},"canonical_sha256":"013e993bf497f46b275dc46aa93ea5cef4de8d472d0f9d99102e26007822f364","source":{"kind":"arxiv","id":"2607.05184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05184","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05184v1","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05184","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"AE7JSO7US72G","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"AE7JSO7US72GWJ25","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"AE7JSO7U","created_at":"2026-07-07T03:19:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AE7JSO7US72GWJ25YRVKSPVFZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:01:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4ad7b4aa4741bf92f39ee5bfd602b38849959b2837198d8d8f8e350e2681e2e2","abstract_canon_sha256":"b594c79ff4302318796e721da7d981906d385c93345b85f7f8356877b209fec2"},"schema_version":"1.0"},"canonical_sha256":"013e993bf497f46b275dc46aa93ea5cef4de8d472d0f9d99102e26007822f364","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:19.005796Z","signature_b64":"TSAUXWYCSPjFQS9JpFS5K1TNmcU3VsIBu9XTq6p/po9hDrwa3rlbdmhRIvDIE0pNDCtZdGSTEV7A0lLwvFXvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"013e993bf497f46b275dc46aa93ea5cef4de8d472d0f9d99102e26007822f364","last_reissued_at":"2026-07-07T03:19:19.005380Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:19.005380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05184","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":"2026-07-07T03:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3iWTFw1gJMKxS3NBsR6lYe87VTJ0XE8ZCk7EoUK8fN8k/3AFtOIk+UKrtGPnh3+3AtkkIEd90dNAp+jJlMyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:42:28.798525Z"},"content_sha256":"b4d7acb9771540de7a320df1ec95a38e3cee5891cc1a201cb9ea300d31fcd373","schema_version":"1.0","event_id":"sha256:b4d7acb9771540de7a320df1ec95a38e3cee5891cc1a201cb9ea300d31fcd373"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AE7JSO7US72GWJ25YRVKSPVFZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking On-Policy Self-Distillation for Thinking Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Liam Fowl, Narutatsu Ri, Sanjeev Arora, Simran Kaur, Yinghui He","submitted_at":"2026-07-06T15:01:35Z","abstract_excerpt":"Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time reasoning to absorb the privileged information. Surprisingly, we show that privileged self-distillation degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17% in avg@1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05184","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/2607.05184/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":"2026-07-07T03:19:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaRHU9+eJWQiv9tGvQjjlgMGiNvMeVAIAn5iLy/rgA2vUET0BZ7Oj0DqrXpcZWjnjEHBCIruB+wxISBKq55bCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:42:28.799048Z"},"content_sha256":"63de06d5631129ca411c32fe6017db28c7a6a4b7a66eea393878eac17e4a885a","schema_version":"1.0","event_id":"sha256:63de06d5631129ca411c32fe6017db28c7a6a4b7a66eea393878eac17e4a885a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AE7JSO7US72GWJ25YRVKSPVFZ3/bundle.json","state_url":"https://pith.science/pith/AE7JSO7US72GWJ25YRVKSPVFZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AE7JSO7US72GWJ25YRVKSPVFZ3/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":"2026-08-06T05:42:28Z","links":{"resolver":"https://pith.science/pith/AE7JSO7US72GWJ25YRVKSPVFZ3","bundle":"https://pith.science/pith/AE7JSO7US72GWJ25YRVKSPVFZ3/bundle.json","state":"https://pith.science/pith/AE7JSO7US72GWJ25YRVKSPVFZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AE7JSO7US72GWJ25YRVKSPVFZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AE7JSO7US72GWJ25YRVKSPVFZ3","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":"b594c79ff4302318796e721da7d981906d385c93345b85f7f8356877b209fec2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:01:35Z","title_canon_sha256":"4ad7b4aa4741bf92f39ee5bfd602b38849959b2837198d8d8f8e350e2681e2e2"},"schema_version":"1.0","source":{"id":"2607.05184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05184","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05184v1","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05184","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"AE7JSO7US72G","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"AE7JSO7US72GWJ25","created_at":"2026-07-07T03:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"AE7JSO7U","created_at":"2026-07-07T03:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:63de06d5631129ca411c32fe6017db28c7a6a4b7a66eea393878eac17e4a885a","target":"graph","created_at":"2026-07-07T03:19:19Z","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/2607.05184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time reasoning to absorb the privileged information. Surprisingly, we show that privileged self-distillation degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17% in avg@1","authors_text":"Liam Fowl, Narutatsu Ri, Sanjeev Arora, Simran Kaur, Yinghui He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:01:35Z","title":"Rethinking On-Policy Self-Distillation for Thinking Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05184","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:b4d7acb9771540de7a320df1ec95a38e3cee5891cc1a201cb9ea300d31fcd373","target":"record","created_at":"2026-07-07T03:19:19Z","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":"b594c79ff4302318796e721da7d981906d385c93345b85f7f8356877b209fec2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T15:01:35Z","title_canon_sha256":"4ad7b4aa4741bf92f39ee5bfd602b38849959b2837198d8d8f8e350e2681e2e2"},"schema_version":"1.0","source":{"id":"2607.05184","kind":"arxiv","version":1}},"canonical_sha256":"013e993bf497f46b275dc46aa93ea5cef4de8d472d0f9d99102e26007822f364","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"013e993bf497f46b275dc46aa93ea5cef4de8d472d0f9d99102e26007822f364","first_computed_at":"2026-07-07T03:19:19.005380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T03:19:19.005380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TSAUXWYCSPjFQS9JpFS5K1TNmcU3VsIBu9XTq6p/po9hDrwa3rlbdmhRIvDIE0pNDCtZdGSTEV7A0lLwvFXvBg==","signature_status":"signed_v1","signed_at":"2026-07-07T03:19:19.005796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d7acb9771540de7a320df1ec95a38e3cee5891cc1a201cb9ea300d31fcd373","sha256:63de06d5631129ca411c32fe6017db28c7a6a4b7a66eea393878eac17e4a885a"],"state_sha256":"68ef56bcbc3733f32ccfdd5b270d01721b0d57b6be2d828e5a33adef591be2e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PLa6wOOxfb/YESMz5SecHDR/seOJSqxuvOY61CswUxuLqXr5HURJ6+TqKZUMKmwS3YQiNtWO/VcDE7TuLNPpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:42:28.802947Z","bundle_sha256":"9b971c043fee7bca24155817609618e6d1b37e8b46e501198d097a89bf658275"}}