{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NQLWE7OF3D6VS4LVQTS7GQQBBB","short_pith_number":"pith:NQLWE7OF","canonical_record":{"source":{"id":"2502.20379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T18:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"d4259c872614fb420c6d79864f552805cc4ad6702098fbdc8e2ece5e203f3a54","abstract_canon_sha256":"d595c6874caab7aa918affc0ef5e38ea95d32a9ac5fb72157169bbac9a945788"},"schema_version":"1.0"},"canonical_sha256":"6c17627dc5d8fd59717584e5f3420108631fc265ea3aac745685e45efcadb664","source":{"kind":"arxiv","id":"2502.20379","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20379","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20379v1","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20379","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"pith_short_12","alias_value":"NQLWE7OF3D6V","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"pith_short_16","alias_value":"NQLWE7OF3D6VS4LV","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"pith_short_8","alias_value":"NQLWE7OF","created_at":"2026-07-05T10:21:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NQLWE7OF3D6VS4LVQTS7GQQBBB","target":"record","payload":{"canonical_record":{"source":{"id":"2502.20379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T18:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"d4259c872614fb420c6d79864f552805cc4ad6702098fbdc8e2ece5e203f3a54","abstract_canon_sha256":"d595c6874caab7aa918affc0ef5e38ea95d32a9ac5fb72157169bbac9a945788"},"schema_version":"1.0"},"canonical_sha256":"6c17627dc5d8fd59717584e5f3420108631fc265ea3aac745685e45efcadb664","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:13.996591Z","signature_b64":"oknfa0jKe//fNd/9EftafQXFHVlt43DBvM2+xDmeNBUd2M3eJpoooCYxwqxbMjL6T4J6cNvtk0QEbWmpyuFHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c17627dc5d8fd59717584e5f3420108631fc265ea3aac745685e45efcadb664","last_reissued_at":"2026-07-05T10:21:13.996052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:13.996052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.20379","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":"2026-07-05T10:21:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q40mZxFxHsCLj6k6jh05HJiJwh39Je9xollvk9zcYjrt/Izxl59ouqGKiP/zr1Hlx/iqBP/Qo2FwrvslHodLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:40:04.828669Z"},"content_sha256":"65893049d14aaa4bd185731236355f017a3642d7120dd2c2c46ee7675142b427","schema_version":"1.0","event_id":"sha256:65893049d14aaa4bd185731236355f017a3642d7120dd2c2c46ee7675142b427"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NQLWE7OF3D6VS4LVQTS7GQQBBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Shalev Lifshitz, Sheila A. McIlraith, Yilun Du","submitted_at":"2025-02-27T18:53:30Z","abstract_excerpt":"By utilizing more computational resources at test-time, large language models (LLMs) can improve without additional training. One common strategy uses verifiers to evaluate candidate outputs. In this work, we propose a novel scaling dimension for test-time compute: scaling the number of verifiers. We introduce Multi-Agent Verification (MAV) as a test-time compute paradigm that combines multiple verifiers to improve performance. We propose using Aspect Verifiers (AVs), off-the-shelf LLMs prompted to verify different aspects of outputs, as one possible choice for the verifiers in a MAV system. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20379","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/2502.20379/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":"2026-07-05T10:21:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qb7YFvaNu2K5k1bllLYu8MKCKBMzODS6CNuTsYpzSj332PJeaQWTCNjGnzs0RdpZoU6OYfM9qQew82XqetsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:40:04.829463Z"},"content_sha256":"9bb120812757ef0266c2160040d2fb302a7d42cb8a5a7ddd759d4bf5aee148d3","schema_version":"1.0","event_id":"sha256:9bb120812757ef0266c2160040d2fb302a7d42cb8a5a7ddd759d4bf5aee148d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB/bundle.json","state_url":"https://pith.science/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB/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":"2026-08-04T15:40:04Z","links":{"resolver":"https://pith.science/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB","bundle":"https://pith.science/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB/bundle.json","state":"https://pith.science/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQLWE7OF3D6VS4LVQTS7GQQBBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NQLWE7OF3D6VS4LVQTS7GQQBBB","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":"d595c6874caab7aa918affc0ef5e38ea95d32a9ac5fb72157169bbac9a945788","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T18:53:30Z","title_canon_sha256":"d4259c872614fb420c6d79864f552805cc4ad6702098fbdc8e2ece5e203f3a54"},"schema_version":"1.0","source":{"id":"2502.20379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20379","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20379v1","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20379","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"pith_short_12","alias_value":"NQLWE7OF3D6V","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"pith_short_16","alias_value":"NQLWE7OF3D6VS4LV","created_at":"2026-07-05T10:21:13Z"},{"alias_kind":"pith_short_8","alias_value":"NQLWE7OF","created_at":"2026-07-05T10:21:13Z"}],"graph_snapshots":[{"event_id":"sha256:9bb120812757ef0266c2160040d2fb302a7d42cb8a5a7ddd759d4bf5aee148d3","target":"graph","created_at":"2026-07-05T10:21:13Z","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/2502.20379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By utilizing more computational resources at test-time, large language models (LLMs) can improve without additional training. One common strategy uses verifiers to evaluate candidate outputs. In this work, we propose a novel scaling dimension for test-time compute: scaling the number of verifiers. We introduce Multi-Agent Verification (MAV) as a test-time compute paradigm that combines multiple verifiers to improve performance. We propose using Aspect Verifiers (AVs), off-the-shelf LLMs prompted to verify different aspects of outputs, as one possible choice for the verifiers in a MAV system. A","authors_text":"Shalev Lifshitz, Sheila A. McIlraith, Yilun Du","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T18:53:30Z","title":"Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20379","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":"sha256:65893049d14aaa4bd185731236355f017a3642d7120dd2c2c46ee7675142b427","target":"record","created_at":"2026-07-05T10:21:13Z","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":"d595c6874caab7aa918affc0ef5e38ea95d32a9ac5fb72157169bbac9a945788","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-27T18:53:30Z","title_canon_sha256":"d4259c872614fb420c6d79864f552805cc4ad6702098fbdc8e2ece5e203f3a54"},"schema_version":"1.0","source":{"id":"2502.20379","kind":"arxiv","version":1}},"canonical_sha256":"6c17627dc5d8fd59717584e5f3420108631fc265ea3aac745685e45efcadb664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c17627dc5d8fd59717584e5f3420108631fc265ea3aac745685e45efcadb664","first_computed_at":"2026-07-05T10:21:13.996052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:13.996052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oknfa0jKe//fNd/9EftafQXFHVlt43DBvM2+xDmeNBUd2M3eJpoooCYxwqxbMjL6T4J6cNvtk0QEbWmpyuFHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:13.996591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65893049d14aaa4bd185731236355f017a3642d7120dd2c2c46ee7675142b427","sha256:9bb120812757ef0266c2160040d2fb302a7d42cb8a5a7ddd759d4bf5aee148d3"],"state_sha256":"1ed0168dbb93526847c0053dfb42fca7be6cfd0a7420efb9d4a6c15483245810"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0E37LELOwYPOzK83GokHN8xrdW0rXBaw84mL00Tz2t0uCpAimlqrBHymquP7iF1WhpNow9yBRtoD5q08YwCwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:40:04.841101Z","bundle_sha256":"79c56281fedf1c204f3c4c7bcebe0037932399cd7a5850ea379a60701d406fa1"}}