{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VM3TJCKLJ7PFJTJQOGP372PP3A","short_pith_number":"pith:VM3TJCKL","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"},"canonical_sha256":"ab3734894b4fde54cd30719fbfe9efd81cd70ac968a249e456889f8f04844222","source":{"kind":"arxiv","id":"2607.28077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28077","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28077v1","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28077","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"VM3TJCKLJ7PF","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"VM3TJCKLJ7PFJTJQ","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"VM3TJCKL","created_at":"2026-07-31T01:35:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VM3TJCKLJ7PFJTJQOGP372PP3A","target":"record","payload":{"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"},"canonical_sha256":"ab3734894b4fde54cd30719fbfe9efd81cd70ac968a249e456889f8f04844222","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"},"source_kind":"arxiv","source_id":"2607.28077","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":"2026-07-31T01:35:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoLd0arhy0RvOYdJ4Y71r916g8AZiPZIZj+5Z1EqcacxEi3VZFOSj/EfKJRHweMzbF3A4W1wTKLaFt3PHAc8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:21.503273Z"},"content_sha256":"cd501c54f4b1fb447980fd024753b10cab696f19c5b3ac740b1c8d967274664c","schema_version":"1.0","event_id":"sha256:cd501c54f4b1fb447980fd024753b10cab696f19c5b3ac740b1c8d967274664c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VM3TJCKLJ7PFJTJQOGP372PP3A","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJTRFRPW1sFw7knPj1CYbFVnzZgihrUCIrSBnf2XZkwUScJ4pqbu1TdoNy4S1eeQ5m4llHiBwGQIJBRAoqmiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:21.503771Z"},"content_sha256":"3a0ed0fdb7b9277f437bc93b4ac53d7e06bafab961e9e6241a7c4e99b36f9b69","schema_version":"1.0","event_id":"sha256:3a0ed0fdb7b9277f437bc93b4ac53d7e06bafab961e9e6241a7c4e99b36f9b69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/bundle.json","state_url":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/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":"2026-08-11T13:04:21Z","links":{"resolver":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A","bundle":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/bundle.json","state":"https://pith.science/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VM3TJCKLJ7PFJTJQOGP372PP3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VM3TJCKLJ7PFJTJQOGP372PP3A","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":"5ca634331c4e6a8895ba67dac7cd939d8bdddc1d09de8457b293819288212568","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T11:50:10Z","title_canon_sha256":"5be70659af0d9df8b70b8605ef11aefe3f5b1b961bc2ecda1dd1c57c44446c70"},"schema_version":"1.0","source":{"id":"2607.28077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28077","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28077v1","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28077","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"VM3TJCKLJ7PF","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"VM3TJCKLJ7PFJTJQ","created_at":"2026-07-31T01:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"VM3TJCKL","created_at":"2026-07-31T01:35:34Z"}],"graph_snapshots":[{"event_id":"sha256:3a0ed0fdb7b9277f437bc93b4ac53d7e06bafab961e9e6241a7c4e99b36f9b69","target":"graph","created_at":"2026-07-31T01:35:34Z","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/2607.28077/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 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","authors_text":"Guowei Wang, Haoyang Zhou, Shuang Liang, Xiting Wang, Yifan Gong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T11:50:10Z","title":"LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28077","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:cd501c54f4b1fb447980fd024753b10cab696f19c5b3ac740b1c8d967274664c","target":"record","created_at":"2026-07-31T01:35:34Z","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":"5ca634331c4e6a8895ba67dac7cd939d8bdddc1d09de8457b293819288212568","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T11:50:10Z","title_canon_sha256":"5be70659af0d9df8b70b8605ef11aefe3f5b1b961bc2ecda1dd1c57c44446c70"},"schema_version":"1.0","source":{"id":"2607.28077","kind":"arxiv","version":1}},"canonical_sha256":"ab3734894b4fde54cd30719fbfe9efd81cd70ac968a249e456889f8f04844222","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab3734894b4fde54cd30719fbfe9efd81cd70ac968a249e456889f8f04844222","first_computed_at":"2026-07-31T01:35:34.197888Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:34.197888Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd501c54f4b1fb447980fd024753b10cab696f19c5b3ac740b1c8d967274664c","sha256:3a0ed0fdb7b9277f437bc93b4ac53d7e06bafab961e9e6241a7c4e99b36f9b69"],"state_sha256":"6ea5b60c5cccb859b79f8ac765065f2c8507b810ad9199906903b67f1c3afc49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XL66I4WJ1jTW/+qERFXYMc9yDPzIAkIcptPtV+Y1nHUYgSG7Ev+oYze0dxCi5E5Knjf4H2gDLxnh5xbjnmagCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:04:21.508610Z","bundle_sha256":"0c0141fe4c7043f8128563ff2c71d0eac66dab874c78a442e349dc9c0797787f"}}