{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:THVPHY5FPNV6Z6JXCFHSAIKJGJ","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":"c930164c00802c195f07d9fa44ee013f5a803b80f1f9bfce9ba9730d71143ee3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T07:16:43Z","title_canon_sha256":"cb8cff54fd97f370aa41c2d27c89fea089de84c6b12b813c8cd1f13f072d5548"},"schema_version":"1.0","source":{"id":"2607.09153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09153","created_at":"2026-07-13T01:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09153v1","created_at":"2026-07-13T01:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09153","created_at":"2026-07-13T01:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"THVPHY5FPNV6","created_at":"2026-07-13T01:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"THVPHY5FPNV6Z6JX","created_at":"2026-07-13T01:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"THVPHY5F","created_at":"2026-07-13T01:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:44353e715c9d8efdbf8a3af64a2f4462442c1ab486bf67882b2e92d09b93f481","target":"graph","created_at":"2026-07-13T01:18:46Z","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/2607.09153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely limiting PRMs' application in long-context scenarios. To resolve this, we introduce KV-PRM, a highly efficient process reward model that eliminates the heavy ","authors_text":"Haibo Jin, Haohan Wang, Kaidi Xu, Peng Kuang, Xiaopeng Yuan, Xiaoyu Han, Yanli Wang, Ye Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T07:16:43Z","title":"KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09153","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:a95b778a0699c1a84ca1296083732681f7fd7c83fd76697ac9bd1a9d62592ad9","target":"record","created_at":"2026-07-13T01:18:46Z","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":"c930164c00802c195f07d9fa44ee013f5a803b80f1f9bfce9ba9730d71143ee3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T07:16:43Z","title_canon_sha256":"cb8cff54fd97f370aa41c2d27c89fea089de84c6b12b813c8cd1f13f072d5548"},"schema_version":"1.0","source":{"id":"2607.09153","kind":"arxiv","version":1}},"canonical_sha256":"99eaf3e3a57b6becf937114f202149326ca0b47b1c0f3fb094c060f104c93571","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99eaf3e3a57b6becf937114f202149326ca0b47b1c0f3fb094c060f104c93571","first_computed_at":"2026-07-13T01:18:46.989257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:18:46.989257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N0Q4vKtRHfMR/EfHR+oiZaeyceoAE8PKbgQxNm07NqlHkex6+AZX80Y26/Cf0tK53oIFo8uswRoL6waBL/qjCQ==","signature_status":"signed_v1","signed_at":"2026-07-13T01:18:46.990411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a95b778a0699c1a84ca1296083732681f7fd7c83fd76697ac9bd1a9d62592ad9","sha256:44353e715c9d8efdbf8a3af64a2f4462442c1ab486bf67882b2e92d09b93f481"],"state_sha256":"9af5e9f0b2a5578e388c955084b28a869c4527809bc31081cb67313b6ee80c7a"}