{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VM3TJCKLJ7PFJTJQOGP372PP3A","short_pith_number":"pith:VM3TJCKL","schema_version":"1.0","canonical_sha256":"ab3734894b4fde54cd30719fbfe9efd81cd70ac968a249e456889f8f04844222","source":{"kind":"arxiv","id":"2607.28077","version":1},"attestation_state":"computed","paper":{"title":"LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guowei Wang, Haoyang Zhou, Shuang Liang, Xiting Wang, Yifan Gong","submitted_at":"2026-07-30T11:50:10Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation. However, existing pre-rollout methods struggle to balance exploitation and exploration: repeatedly exploiting historically informative prompts can narrow training coverage, whereas broader exploration can lower the fraction of informative prompts. To address these limitatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.28077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T11:50:10Z","cross_cats_sorted":[],"title_canon_sha256":"5be70659af0d9df8b70b8605ef11aefe3f5b1b961bc2ecda1dd1c57c44446c70","abstract_canon_sha256":"5ca634331c4e6a8895ba67dac7cd939d8bdddc1d09de8457b293819288212568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab3734894b4fde54cd30719fbfe9efd81cd70ac968a249e456889f8f04844222","last_reissued_at":"2026-07-31T01:35:34.197888Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:34.197888Z"},"graph_snapshot":{"paper":{"title":"LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guowei Wang, Haoyang Zhou, Shuang Liang, Xiting Wang, Yifan Gong","submitted_at":"2026-07-30T11:50:10Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation. However, existing pre-rollout methods struggle to balance exploitation and exploration: repeatedly exploiting historically informative prompts can narrow training coverage, whereas broader exploration can lower the fraction of informative prompts. To address these limitatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28077","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/2607.28077/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.28077","created_at":"2026-07-31T01:35:34.201004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28077v1","created_at":"2026-07-31T01:35:34.201004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28077","created_at":"2026-07-31T01:35:34.201004+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM3TJCKLJ7PF","created_at":"2026-07-31T01:35:34.201004+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM3TJCKLJ7PFJTJQ","created_at":"2026-07-31T01:35:34.201004+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM3TJCKL","created_at":"2026-07-31T01:35:34.201004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A","json":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A.json","graph_json":"https://pith.science/api/pith-number/VM3TJCKLJ7PFJTJQOGP372PP3A/graph.json","events_json":"https://pith.science/api/pith-number/VM3TJCKLJ7PFJTJQOGP372PP3A/events.json","paper":"https://pith.science/paper/VM3TJCKL"},"agent_actions":{"view_html":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A","download_json":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A.json","view_paper":"https://pith.science/paper/VM3TJCKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28077&json=true","fetch_graph":"https://pith.science/api/pith-number/VM3TJCKLJ7PFJTJQOGP372PP3A/graph.json","fetch_events":"https://pith.science/api/pith-number/VM3TJCKLJ7PFJTJQOGP372PP3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/action/storage_attestation","attest_author":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/action/author_attestation","sign_citation":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/action/citation_signature","submit_replication":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/action/replication_record"}},"created_at":"2026-07-31T01:35:34.201004+00:00","updated_at":"2026-07-31T01:35:34.201004+00:00"}