{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:244GEGHRXJEL33QNB6H7YXFRYW","short_pith_number":"pith:244GEGHR","canonical_record":{"source":{"id":"2608.11368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T19:24:59Z","cross_cats_sorted":[],"title_canon_sha256":"74425054b8964568a9dc09a49ba801f115cb870a166071dbfbbcc757761a2143","abstract_canon_sha256":"0362ce8f1c38e7dcc7d3aa28aa93ab9324120b0c1aa9ab9b261fb5153fde55ad"},"schema_version":"1.0"},"canonical_sha256":"d7386218f1ba48bdee0d0f8ffc5cb1c59ee35f7174ed03bd49af90ad9129453c","source":{"kind":"arxiv","id":"2608.11368","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11368","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11368v1","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11368","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"pith_short_12","alias_value":"244GEGHRXJEL","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"pith_short_16","alias_value":"244GEGHRXJEL33QN","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"pith_short_8","alias_value":"244GEGHR","created_at":"2026-08-13T00:21:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:244GEGHRXJEL33QNB6H7YXFRYW","target":"record","payload":{"canonical_record":{"source":{"id":"2608.11368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T19:24:59Z","cross_cats_sorted":[],"title_canon_sha256":"74425054b8964568a9dc09a49ba801f115cb870a166071dbfbbcc757761a2143","abstract_canon_sha256":"0362ce8f1c38e7dcc7d3aa28aa93ab9324120b0c1aa9ab9b261fb5153fde55ad"},"schema_version":"1.0"},"canonical_sha256":"d7386218f1ba48bdee0d0f8ffc5cb1c59ee35f7174ed03bd49af90ad9129453c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:21:42.069435Z","signature_b64":"/rGRdzHCHmlW3czGXLQs7EY7mfoB7WHjzkTQccfYLhgpoI0Ey6u7H4s4vmIKjPz+bCMl40d8QJz9JrbVa3e5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7386218f1ba48bdee0d0f8ffc5cb1c59ee35f7174ed03bd49af90ad9129453c","last_reissued_at":"2026-08-13T00:21:42.065265Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:21:42.065265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.11368","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":"2026-08-13T00:21:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"93TYgxuZeZebvoPjy1awphalOTKHRlNYOfeJQvtc7tONADt9VE6NBaW69ycJ6ArXcdoeZJcE7IOfQaeO4DiADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:49:28.128622Z"},"content_sha256":"a77f20ada66f90c4cb5cb6615830956a3c3f5c1012c08827dfe9a39f0023d81f","schema_version":"1.0","event_id":"sha256:a77f20ada66f90c4cb5cb6615830956a3c3f5c1012c08827dfe9a39f0023d81f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:244GEGHRXJEL33QNB6H7YXFRYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elena Voss, Marcus Hale, Pixel Nomand, Sofia Reyes","submitted_at":"2026-08-11T19:24:59Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) spends most of its compute generating groups of long reasoning trajectories. Recent allocators reduce this cost by assigning budgets to prompts, rollouts, or tokens according to a pointwise notion of difficulty or utility. We identify a statistical mismatch: the unclipped leave-one-out group-relative score gradient is not a sum of independent point contributions, but a second-order U-statistic over pairs of rollouts. Completing one rollout therefore reveals contrast with every other completed rollout, and adaptive endpoint selection changes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11368","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/2608.11368/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":"2026-08-13T00:21:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+b8bDi3wAFkYtJmswl1EsF0v0EgpyDqky7j9er7iLoWnZxwZtewiyt+vnZ37id4ze7b9nSRM9iYn7pQej0zDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:49:28.129377Z"},"content_sha256":"df6e5e07055c02e17e93cf1ff1acd0b25e5ee07ced38d6fd24565cf3554c4b47","schema_version":"1.0","event_id":"sha256:df6e5e07055c02e17e93cf1ff1acd0b25e5ee07ced38d6fd24565cf3554c4b47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/244GEGHRXJEL33QNB6H7YXFRYW/bundle.json","state_url":"https://pith.science/pith/244GEGHRXJEL33QNB6H7YXFRYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/244GEGHRXJEL33QNB6H7YXFRYW/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":"2026-08-18T01:49:28Z","links":{"resolver":"https://pith.science/pith/244GEGHRXJEL33QNB6H7YXFRYW","bundle":"https://pith.science/pith/244GEGHRXJEL33QNB6H7YXFRYW/bundle.json","state":"https://pith.science/pith/244GEGHRXJEL33QNB6H7YXFRYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/244GEGHRXJEL33QNB6H7YXFRYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:244GEGHRXJEL33QNB6H7YXFRYW","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":"0362ce8f1c38e7dcc7d3aa28aa93ab9324120b0c1aa9ab9b261fb5153fde55ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T19:24:59Z","title_canon_sha256":"74425054b8964568a9dc09a49ba801f115cb870a166071dbfbbcc757761a2143"},"schema_version":"1.0","source":{"id":"2608.11368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11368","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11368v1","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11368","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"pith_short_12","alias_value":"244GEGHRXJEL","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"pith_short_16","alias_value":"244GEGHRXJEL33QN","created_at":"2026-08-13T00:21:42Z"},{"alias_kind":"pith_short_8","alias_value":"244GEGHR","created_at":"2026-08-13T00:21:42Z"}],"graph_snapshots":[{"event_id":"sha256:df6e5e07055c02e17e93cf1ff1acd0b25e5ee07ced38d6fd24565cf3554c4b47","target":"graph","created_at":"2026-08-13T00:21:42Z","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/2608.11368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) spends most of its compute generating groups of long reasoning trajectories. Recent allocators reduce this cost by assigning budgets to prompts, rollouts, or tokens according to a pointwise notion of difficulty or utility. We identify a statistical mismatch: the unclipped leave-one-out group-relative score gradient is not a sum of independent point contributions, but a second-order U-statistic over pairs of rollouts. Completing one rollout therefore reveals contrast with every other completed rollout, and adaptive endpoint selection changes","authors_text":"Elena Voss, Marcus Hale, Pixel Nomand, Sofia Reyes","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T19:24:59Z","title":"PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11368","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:a77f20ada66f90c4cb5cb6615830956a3c3f5c1012c08827dfe9a39f0023d81f","target":"record","created_at":"2026-08-13T00:21:42Z","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":"0362ce8f1c38e7dcc7d3aa28aa93ab9324120b0c1aa9ab9b261fb5153fde55ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T19:24:59Z","title_canon_sha256":"74425054b8964568a9dc09a49ba801f115cb870a166071dbfbbcc757761a2143"},"schema_version":"1.0","source":{"id":"2608.11368","kind":"arxiv","version":1}},"canonical_sha256":"d7386218f1ba48bdee0d0f8ffc5cb1c59ee35f7174ed03bd49af90ad9129453c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7386218f1ba48bdee0d0f8ffc5cb1c59ee35f7174ed03bd49af90ad9129453c","first_computed_at":"2026-08-13T00:21:42.065265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:21:42.065265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/rGRdzHCHmlW3czGXLQs7EY7mfoB7WHjzkTQccfYLhgpoI0Ey6u7H4s4vmIKjPz+bCMl40d8QJz9JrbVa3e5Ag==","signature_status":"signed_v1","signed_at":"2026-08-13T00:21:42.069435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a77f20ada66f90c4cb5cb6615830956a3c3f5c1012c08827dfe9a39f0023d81f","sha256:df6e5e07055c02e17e93cf1ff1acd0b25e5ee07ced38d6fd24565cf3554c4b47"],"state_sha256":"e638f6a8501498ac09c9ae5ebf0eda5984e7fdfbb7272394f0527d5be23f3c73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDS9qc4H4UYhzvy5Db3klLIDv7HqC7Lxic32N3s3oC6MlqLZqKfYnpVpFD3ChnFQR4oqoAX7842q64LkC2ftDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:49:28.136840Z","bundle_sha256":"0eb623193ba06b1c035567c5f3da8ea32ddef486d7a03341364234e84f5d5adc"}}