{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4WYYRWG72XBPX3SWIEDXAJUZJ","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":"f1a99d5337614eef4dda07a5ff9823e896d576cb43352659b3a8087b8dd313bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T17:28:40Z","title_canon_sha256":"d7e5352ed458628a7ad3a00bfbbd1a828f42e4c5d787059c6f118c37dce180df"},"schema_version":"1.0","source":{"id":"2607.19313","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19313","created_at":"2026-07-22T01:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19313v1","created_at":"2026-07-22T01:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19313","created_at":"2026-07-22T01:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"M4WYYRWG72XB","created_at":"2026-07-22T01:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"M4WYYRWG72XBPX3S","created_at":"2026-07-22T01:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"M4WYYRWG","created_at":"2026-07-22T01:24:36Z"}],"graph_snapshots":[{"event_id":"sha256:09bfdc522a623b2e45c7b8d437a454466ceb10a4a2738f80dcf62b77e037a4f8","target":"graph","created_at":"2026-07-22T01:24:36Z","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/2607.19313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot generate any correct solutions, it receives \\textit{zero} learning signal. Providing privileged guidance during training, such as solution prefixes, can help overcome this learning cliff by steering the model towards {correct solutions with non-zero reward}. {We call these rollouts \\textit{off-context}: they are generated from a training prompt that contains privileged guidance, while the target objective is defined by t","authors_text":"Aditya Modi, Ankur Samanta, Daniel Jiang, Jalaj Bhandari, Kavosh Asadi, Priyank Agrawal, Shervin Ghasemlou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T17:28:40Z","title":"Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19313","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:ac10e1db6db28e3b1462eae85db386c5316acb0c774edd958a661f384fc1a271","target":"record","created_at":"2026-07-22T01:24:36Z","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":"f1a99d5337614eef4dda07a5ff9823e896d576cb43352659b3a8087b8dd313bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T17:28:40Z","title_canon_sha256":"d7e5352ed458628a7ad3a00bfbbd1a828f42e4c5d787059c6f118c37dce180df"},"schema_version":"1.0","source":{"id":"2607.19313","kind":"arxiv","version":1}},"canonical_sha256":"672d8c46c6feae17df72b2083b8134ca6d4447295b4285f1d62cde618ae46459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"672d8c46c6feae17df72b2083b8134ca6d4447295b4285f1d62cde618ae46459","first_computed_at":"2026-07-22T01:24:36.198189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:36.198189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Va0T97Q03iQsW0Wj8+N1HuI5Upfv4TKGZvgB1ikInk2UAE3xK1y7UGxTgHzmOlyMsMa4+YOUO0xWTRs6h3eZBg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:36.199145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19313","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac10e1db6db28e3b1462eae85db386c5316acb0c774edd958a661f384fc1a271","sha256:09bfdc522a623b2e45c7b8d437a454466ceb10a4a2738f80dcf62b77e037a4f8"],"state_sha256":"285f16dc7258c9a489aa1189793271a589fecb5bdca5f4aafbcf0f5e56da280b"}