{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6R7T665FYOK3NW6J3W5WRSUDYX","short_pith_number":"pith:6R7T665F","canonical_record":{"source":{"id":"2605.28295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:46:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"bf99be4021686ec7eead92551640ae205ea295d7ab1afdcbcf6f6ac6783d1aea","abstract_canon_sha256":"fd37b9e08d1ba0a5e233dc0e1e2b05d38a3b4e5b7536b416674352be32530589"},"schema_version":"1.0"},"canonical_sha256":"f47f3f7ba5c395b6dbc9ddbb68ca83c5c69fc930428e486595b5f3a380f31eb2","source":{"kind":"arxiv","id":"2605.28295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28295","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28295v1","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28295","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"6R7T665FYOK3","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"6R7T665FYOK3NW6J","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"6R7T665F","created_at":"2026-05-28T01:05:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6R7T665FYOK3NW6J3W5WRSUDYX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:46:01Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"bf99be4021686ec7eead92551640ae205ea295d7ab1afdcbcf6f6ac6783d1aea","abstract_canon_sha256":"fd37b9e08d1ba0a5e233dc0e1e2b05d38a3b4e5b7536b416674352be32530589"},"schema_version":"1.0"},"canonical_sha256":"f47f3f7ba5c395b6dbc9ddbb68ca83c5c69fc930428e486595b5f3a380f31eb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:05.491326Z","signature_b64":"+SFXn9MGkD9VDGuQT2ahRBHMEwVHPf/tcW87OiCHZPMQIG75AHeIU6qjY/DsxUyLFfHf+V+nWA9pXesPII/GCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f47f3f7ba5c395b6dbc9ddbb68ca83c5c69fc930428e486595b5f3a380f31eb2","last_reissued_at":"2026-05-28T01:05:05.490791Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:05.490791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28295","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":"2026-05-28T01:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+XcjwFbo1khWIugtxkVcmKnpKfEdJ+2jd6sQE9NO6fbR4OZUMjueytyztTJKuFVMGo6SICkUdGsNVfJPrDyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:53:30.806827Z"},"content_sha256":"308517e40a61504576fd8226e031ca2ef53e33d85cb8d7c55f01414f99c0e843","schema_version":"1.0","event_id":"sha256:308517e40a61504576fd8226e031ca2ef53e33d85cb8d7c55f01414f99c0e843"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6R7T665FYOK3NW6J3W5WRSUDYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Albert No, Soeun Kim","submitted_at":"2026-05-27T10:46:01Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the policy to alternative reasoning paths and a verifier to score them. Rollout diversity has accordingly emerged as a central bottleneck in RLVR, with most existing methods broadening exploration through temperature, prefix, or rollout-selection adjustments. We identify a structurally distinguished but overlooked position for broadening this diversity: the first token after the reasoning marker. The policy's first-token distribution exhibits a sharp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28295","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/2605.28295/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":"2026-05-28T01:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUThM7IhCpN0iV/E2MANYXOrMm7M+nCtih45SSBIQlMVJ8DPU5HnjcXwj38eG2KVnamo3SyNLDRkTjTGIid0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:53:30.807200Z"},"content_sha256":"aa5939438286728bfc9a1a59681af3ac6a41d2cf149c6b67ce53037fa1f29537","schema_version":"1.0","event_id":"sha256:aa5939438286728bfc9a1a59681af3ac6a41d2cf149c6b67ce53037fa1f29537"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6R7T665FYOK3NW6J3W5WRSUDYX/bundle.json","state_url":"https://pith.science/pith/6R7T665FYOK3NW6J3W5WRSUDYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6R7T665FYOK3NW6J3W5WRSUDYX/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":"2026-06-01T07:53:30Z","links":{"resolver":"https://pith.science/pith/6R7T665FYOK3NW6J3W5WRSUDYX","bundle":"https://pith.science/pith/6R7T665FYOK3NW6J3W5WRSUDYX/bundle.json","state":"https://pith.science/pith/6R7T665FYOK3NW6J3W5WRSUDYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6R7T665FYOK3NW6J3W5WRSUDYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6R7T665FYOK3NW6J3W5WRSUDYX","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":"fd37b9e08d1ba0a5e233dc0e1e2b05d38a3b4e5b7536b416674352be32530589","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:46:01Z","title_canon_sha256":"bf99be4021686ec7eead92551640ae205ea295d7ab1afdcbcf6f6ac6783d1aea"},"schema_version":"1.0","source":{"id":"2605.28295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28295","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28295v1","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28295","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"6R7T665FYOK3","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"6R7T665FYOK3NW6J","created_at":"2026-05-28T01:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"6R7T665F","created_at":"2026-05-28T01:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:aa5939438286728bfc9a1a59681af3ac6a41d2cf149c6b67ce53037fa1f29537","target":"graph","created_at":"2026-05-28T01:05:05Z","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/2605.28295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the policy to alternative reasoning paths and a verifier to score them. Rollout diversity has accordingly emerged as a central bottleneck in RLVR, with most existing methods broadening exploration through temperature, prefix, or rollout-selection adjustments. We identify a structurally distinguished but overlooked position for broadening this diversity: the first token after the reasoning marker. The policy's first-token distribution exhibits a sharp","authors_text":"Albert No, Soeun Kim","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:46:01Z","title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28295","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":"sha256:308517e40a61504576fd8226e031ca2ef53e33d85cb8d7c55f01414f99c0e843","target":"record","created_at":"2026-05-28T01:05:05Z","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":"fd37b9e08d1ba0a5e233dc0e1e2b05d38a3b4e5b7536b416674352be32530589","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:46:01Z","title_canon_sha256":"bf99be4021686ec7eead92551640ae205ea295d7ab1afdcbcf6f6ac6783d1aea"},"schema_version":"1.0","source":{"id":"2605.28295","kind":"arxiv","version":1}},"canonical_sha256":"f47f3f7ba5c395b6dbc9ddbb68ca83c5c69fc930428e486595b5f3a380f31eb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f47f3f7ba5c395b6dbc9ddbb68ca83c5c69fc930428e486595b5f3a380f31eb2","first_computed_at":"2026-05-28T01:05:05.490791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:05.490791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+SFXn9MGkD9VDGuQT2ahRBHMEwVHPf/tcW87OiCHZPMQIG75AHeIU6qjY/DsxUyLFfHf+V+nWA9pXesPII/GCw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:05.491326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:308517e40a61504576fd8226e031ca2ef53e33d85cb8d7c55f01414f99c0e843","sha256:aa5939438286728bfc9a1a59681af3ac6a41d2cf149c6b67ce53037fa1f29537"],"state_sha256":"84ae0d4076aad25c1f6fd7279d68885c2d819031ae72e820df5767af69dbb50f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aE8U8GJL+0F1GIZoiZMsoVUW6qkXfWyi4ZXBRJmkQYAEstx8+TaNHNbGq6lCjuRxvfAlbGzQoxOQzGaZ5B6SDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:53:30.809162Z","bundle_sha256":"0791e365326b7afd9fbc59c6a017de378e8f40a44917fb1fbb71d2f9cb27b6a4"}}