{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GYF35QAHRV6X47RXAK6ND45HAZ","short_pith_number":"pith:GYF35QAH","canonical_record":{"source":{"id":"2505.11966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T11:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"613c3154f5ab88ae81c2568fa58dd61c9a8356838ff53df5f190cac7e315c690","abstract_canon_sha256":"0e0c2cecacb49b9d8e61378ce5d8c2e6d424c1593df6dd87e2ffcedbea48fef6"},"schema_version":"1.0"},"canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","source":{"kind":"arxiv","id":"2505.11966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11966","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11966v1","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11966","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"GYF35QAHRV6X","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"GYF35QAHRV6X47RX","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"GYF35QAH","created_at":"2026-07-05T11:04:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GYF35QAHRV6X47RXAK6ND45HAZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T11:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"613c3154f5ab88ae81c2568fa58dd61c9a8356838ff53df5f190cac7e315c690","abstract_canon_sha256":"0e0c2cecacb49b9d8e61378ce5d8c2e6d424c1593df6dd87e2ffcedbea48fef6"},"schema_version":"1.0"},"canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:55.577986Z","signature_b64":"b+tOTRvlFG3fadSn5Sj/2BNNfBCV5qnOd+SZ7x4vKnQDjkEvrHEl6buHCrd5L/fjJFSK+h5km8H43anhwC4RBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","last_reissued_at":"2026-07-05T11:04:55.577586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:55.577586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11966","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":"2026-07-05T11:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G94QGcmQNt0iVUFNApDnAxOeTy/bD78K1fDkoMm2ynoVO70BLoS9PgJ7tHZP7szQuoMw8n5IISIrlXtpVHTGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:29.702968Z"},"content_sha256":"cc00a5da53eafc15c3583ebeed2ebcf991dcaa500fabcb794860b860774e664d","schema_version":"1.0","event_id":"sha256:cc00a5da53eafc15c3583ebeed2ebcf991dcaa500fabcb794860b860774e664d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GYF35QAHRV6X47RXAK6ND45HAZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianyuan Zhong, Kezhi Li, Qiang Xu, XiangYu Wen, Zeju Li, Zhijian Xu","submitted_at":"2025-05-17T11:41:44Z","abstract_excerpt":"Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates this landscape by introducing its own challenging trade-off: sophisticated Generative Reward Models (GenRMs) can be computationally prohibitive if naively integrated with LLMs at test-time, while simpler, faster methods may lack reliability. To overcome these challenges, we introduce FlexiVe, a novel generative verifier that flexibly balances computational re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11966","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/2505.11966/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":"2026-07-05T11:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qduUyHZZlWaVzJCqdrr139F8SDkqWzzMTHR2GXH6KJ1VtDuQPGjyWws1M0LnD6JTA404ZSSLazX7n5dnAprABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:29.703470Z"},"content_sha256":"3b20984d423484fdadb67234a0f05c3fbc5ba94671a7319482c1dd712fc51044","schema_version":"1.0","event_id":"sha256:3b20984d423484fdadb67234a0f05c3fbc5ba94671a7319482c1dd712fc51044"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/bundle.json","state_url":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYF35QAHRV6X47RXAK6ND45HAZ/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":"2026-08-09T05:16:29Z","links":{"resolver":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ","bundle":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/bundle.json","state":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYF35QAHRV6X47RXAK6ND45HAZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GYF35QAHRV6X47RXAK6ND45HAZ","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":"0e0c2cecacb49b9d8e61378ce5d8c2e6d424c1593df6dd87e2ffcedbea48fef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T11:41:44Z","title_canon_sha256":"613c3154f5ab88ae81c2568fa58dd61c9a8356838ff53df5f190cac7e315c690"},"schema_version":"1.0","source":{"id":"2505.11966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11966","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11966v1","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11966","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"GYF35QAHRV6X","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"GYF35QAHRV6X47RX","created_at":"2026-07-05T11:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"GYF35QAH","created_at":"2026-07-05T11:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:3b20984d423484fdadb67234a0f05c3fbc5ba94671a7319482c1dd712fc51044","target":"graph","created_at":"2026-07-05T11:04:55Z","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/2505.11966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates this landscape by introducing its own challenging trade-off: sophisticated Generative Reward Models (GenRMs) can be computationally prohibitive if naively integrated with LLMs at test-time, while simpler, faster methods may lack reliability. To overcome these challenges, we introduce FlexiVe, a novel generative verifier that flexibly balances computational re","authors_text":"Jianyuan Zhong, Kezhi Li, Qiang Xu, XiangYu Wen, Zeju Li, Zhijian Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T11:41:44Z","title":"Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11966","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:cc00a5da53eafc15c3583ebeed2ebcf991dcaa500fabcb794860b860774e664d","target":"record","created_at":"2026-07-05T11:04:55Z","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":"0e0c2cecacb49b9d8e61378ce5d8c2e6d424c1593df6dd87e2ffcedbea48fef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T11:41:44Z","title_canon_sha256":"613c3154f5ab88ae81c2568fa58dd61c9a8356838ff53df5f190cac7e315c690"},"schema_version":"1.0","source":{"id":"2505.11966","kind":"arxiv","version":1}},"canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","first_computed_at":"2026-07-05T11:04:55.577586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:55.577586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+tOTRvlFG3fadSn5Sj/2BNNfBCV5qnOd+SZ7x4vKnQDjkEvrHEl6buHCrd5L/fjJFSK+h5km8H43anhwC4RBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:55.577986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc00a5da53eafc15c3583ebeed2ebcf991dcaa500fabcb794860b860774e664d","sha256:3b20984d423484fdadb67234a0f05c3fbc5ba94671a7319482c1dd712fc51044"],"state_sha256":"dd1949f570469373d40cf30143529765bb6d5cfc695b5236eecdce0acdfa9296"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHEwX3hXPSFdSNOfBecISW5yvPzAMRsX1SynzYBj2ygHwv1niLCimnxgRJHiN3QvWCLd+J8nOG5UF2PJtG/yCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:16:29.708372Z","bundle_sha256":"ff290ec25ad4f24032fcae39241f4f2d41e818dc2cf490b81a91bd854e905c69"}}