{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DSQRVSKPTW5OE32EJRXAA7SCHJ","short_pith_number":"pith:DSQRVSKP","canonical_record":{"source":{"id":"2607.22002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T06:04:04Z","cross_cats_sorted":[],"title_canon_sha256":"29493460947821475099083b3bc7a0f0738e2e27ebe5d8a56fb60027a8f7d1de","abstract_canon_sha256":"c4b7896cfd60e5d2650f6c42bb6a26e6e22be35be2b687fc8d8f5d936d102306"},"schema_version":"1.0"},"canonical_sha256":"1ca11ac94f9dbae26f444c6e007e423a472da6a7e58a654abc83d09df24609b8","source":{"kind":"arxiv","id":"2607.22002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22002","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22002v1","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22002","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"DSQRVSKPTW5O","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"DSQRVSKPTW5OE32E","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"DSQRVSKP","created_at":"2026-07-27T01:20:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DSQRVSKPTW5OE32EJRXAA7SCHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T06:04:04Z","cross_cats_sorted":[],"title_canon_sha256":"29493460947821475099083b3bc7a0f0738e2e27ebe5d8a56fb60027a8f7d1de","abstract_canon_sha256":"c4b7896cfd60e5d2650f6c42bb6a26e6e22be35be2b687fc8d8f5d936d102306"},"schema_version":"1.0"},"canonical_sha256":"1ca11ac94f9dbae26f444c6e007e423a472da6a7e58a654abc83d09df24609b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:42.622073Z","signature_b64":"YL2JY2YNekOYBwt4ZS3t8/Yq1QcZL8hYI3dY0Kwq80ljwYEZopHRhvxQm8gpO3PLCIShiQta3qGK5Ieg6Af0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca11ac94f9dbae26f444c6e007e423a472da6a7e58a654abc83d09df24609b8","last_reissued_at":"2026-07-27T01:20:42.621183Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:42.621183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22002","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":"2026-07-27T01:20:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4EPIqSgqLp/sNiJM5mgyqkd+KX9hxTvw+P5Qro35Obfi114IPCeUczEn8Obq0tX/yej6+6gt/3GE4fWDX/mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:51:03.984974Z"},"content_sha256":"6951ae5253e359bdf2a7c0d68406dfe3c22a5573c8248bacf3073ae5bd9f0386","schema_version":"1.0","event_id":"sha256:6951ae5253e359bdf2a7c0d68406dfe3c22a5573c8248bacf3073ae5bd9f0386"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DSQRVSKPTW5OE32EJRXAA7SCHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baharan Mirzasoleiman, Henry Liu, Heyang Jiang","submitted_at":"2026-07-24T06:04:04Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has emerged as a highly effective framework for improving LLM reasoning, with methods such as GRPO among its most successful instantiations. However, GRPO relies on repeated generation of long chain-of-thought rollouts. Training time scales with the number of rollouts, a large fraction of which are uninformative. Thus, GRPO is computationally expensive and unstable. To mitigate this, existing approaches either generate a larger pool of rollouts and filter the most informative prompts, or leverage historical signals for filtering at later st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22002","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/2607.22002/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":"2026-07-27T01:20:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a1YsV5HETL2hAentu1dgUkTT9VCov545n2EjiixEN5KPKjQI0xsKnXrAjvvTuB8I0lUjxrehTSGW9fQY1DZaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:51:03.985501Z"},"content_sha256":"0f8e57f18877f5eb33aa3220129aa39690574449dff07ab6970ddd64e338e333","schema_version":"1.0","event_id":"sha256:0f8e57f18877f5eb33aa3220129aa39690574449dff07ab6970ddd64e338e333"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ/bundle.json","state_url":"https://pith.science/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ/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":"2026-08-19T04:51:03Z","links":{"resolver":"https://pith.science/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ","bundle":"https://pith.science/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ/bundle.json","state":"https://pith.science/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSQRVSKPTW5OE32EJRXAA7SCHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DSQRVSKPTW5OE32EJRXAA7SCHJ","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":"c4b7896cfd60e5d2650f6c42bb6a26e6e22be35be2b687fc8d8f5d936d102306","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T06:04:04Z","title_canon_sha256":"29493460947821475099083b3bc7a0f0738e2e27ebe5d8a56fb60027a8f7d1de"},"schema_version":"1.0","source":{"id":"2607.22002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22002","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22002v1","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22002","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"DSQRVSKPTW5O","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"DSQRVSKPTW5OE32E","created_at":"2026-07-27T01:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"DSQRVSKP","created_at":"2026-07-27T01:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:0f8e57f18877f5eb33aa3220129aa39690574449dff07ab6970ddd64e338e333","target":"graph","created_at":"2026-07-27T01:20:42Z","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/2607.22002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has emerged as a highly effective framework for improving LLM reasoning, with methods such as GRPO among its most successful instantiations. However, GRPO relies on repeated generation of long chain-of-thought rollouts. Training time scales with the number of rollouts, a large fraction of which are uninformative. Thus, GRPO is computationally expensive and unstable. To mitigate this, existing approaches either generate a larger pool of rollouts and filter the most informative prompts, or leverage historical signals for filtering at later st","authors_text":"Baharan Mirzasoleiman, Henry Liu, Heyang Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T06:04:04Z","title":"Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22002","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":"sha256:6951ae5253e359bdf2a7c0d68406dfe3c22a5573c8248bacf3073ae5bd9f0386","target":"record","created_at":"2026-07-27T01:20:42Z","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":"c4b7896cfd60e5d2650f6c42bb6a26e6e22be35be2b687fc8d8f5d936d102306","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-24T06:04:04Z","title_canon_sha256":"29493460947821475099083b3bc7a0f0738e2e27ebe5d8a56fb60027a8f7d1de"},"schema_version":"1.0","source":{"id":"2607.22002","kind":"arxiv","version":1}},"canonical_sha256":"1ca11ac94f9dbae26f444c6e007e423a472da6a7e58a654abc83d09df24609b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca11ac94f9dbae26f444c6e007e423a472da6a7e58a654abc83d09df24609b8","first_computed_at":"2026-07-27T01:20:42.621183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:42.621183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YL2JY2YNekOYBwt4ZS3t8/Yq1QcZL8hYI3dY0Kwq80ljwYEZopHRhvxQm8gpO3PLCIShiQta3qGK5Ieg6Af0AQ==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:42.622073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6951ae5253e359bdf2a7c0d68406dfe3c22a5573c8248bacf3073ae5bd9f0386","sha256:0f8e57f18877f5eb33aa3220129aa39690574449dff07ab6970ddd64e338e333"],"state_sha256":"7a71e13417206c8b3b6113b8e55032cd6f8c6f1aff808f80439c70dc989c5155"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxF8yKXXihqrirwwRUBIPQEVnNNBNRB9D1GOUzBwY9CeD/OQLidqjbm5+xLQcTcv01nJcmEYsKbxiZ7BGy1XBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:51:03.989964Z","bundle_sha256":"fe47fa3addc0832fdd9a8b693a79dc20f1be9197be63af9542a8352fdd003367"}}