{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SDOMHYLKDXMD3TPJVCP4H3ZUEZ","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":"da4df962d640349c4be6fe0f3f1a985a88af700ecf8a28d7b6f0d087ad242856","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T05:57:47Z","title_canon_sha256":"e95514ed269cafc879a1528f1a4766f9bf2fef48fd15232983654665542abf90"},"schema_version":"1.0","source":{"id":"2507.18973","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18973","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18973v2","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18973","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"SDOMHYLKDXMD","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"pith_short_16","alias_value":"SDOMHYLKDXMD3TPJ","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"pith_short_8","alias_value":"SDOMHYLK","created_at":"2026-07-05T11:57:38Z"}],"graph_snapshots":[{"event_id":"sha256:f0654c71afaa202b51a0ccb0b544c27536900604767fff74e9e57fe85859f521","target":"graph","created_at":"2026-07-05T11:57:38Z","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/2507.18973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Augmenting large language models (LLMs) with external tools is a promising avenue for developing high-performance mathematical reasoning systems. Prior tool-augmented approaches typically finetune an LLM to select and invoke a single tool at each reasoning step and show promising results on simpler math reasoning benchmarks such as GSM8K. However, these approaches struggle with more complex math problems that require precise reasoning over multiple steps. To address this limitation, in this work, we propose Multi-TAG, a Multi-Tool AGgregation-based framework. Instead of relying on a single too","authors_text":"Bohan Yao, Vikas Yadav","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T05:57:47Z","title":"A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18973","kind":"arxiv","version":2},"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:d4f8e51cc973a9ec55fe5fb0e01d5352120e9c89a3540bf39e3ea10fd78daffd","target":"record","created_at":"2026-07-05T11:57:38Z","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":"da4df962d640349c4be6fe0f3f1a985a88af700ecf8a28d7b6f0d087ad242856","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T05:57:47Z","title_canon_sha256":"e95514ed269cafc879a1528f1a4766f9bf2fef48fd15232983654665542abf90"},"schema_version":"1.0","source":{"id":"2507.18973","kind":"arxiv","version":2}},"canonical_sha256":"90dcc3e16a1dd83dcde9a89fc3ef34264a7edf1fa3b971344f816751b003e9d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90dcc3e16a1dd83dcde9a89fc3ef34264a7edf1fa3b971344f816751b003e9d4","first_computed_at":"2026-07-05T11:57:38.139163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:38.139163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQLGs8XPPp0wXZ+a/wEAVo1g7PPR7nFlewai4XpSFsQ7Rev9FF/Jxv9ReC1XfjNAneM60srBQ8EcyZUvf4UhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:38.139853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18973","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4f8e51cc973a9ec55fe5fb0e01d5352120e9c89a3540bf39e3ea10fd78daffd","sha256:f0654c71afaa202b51a0ccb0b544c27536900604767fff74e9e57fe85859f521"],"state_sha256":"753ef4747d9f1a44477ca5e3644d95b5c7db6a5240555eabb9bab637e9287746"}