{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W2FFIX34FAAI2KKJXINRG6KDQN","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":"634dce81fce35264187f86f69fad09f8ec6810c4d5c19d5836e5857c0414de9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T22:10:38Z","title_canon_sha256":"e340b05055e10b6b4d46c28986db6f4f0d1827e3a7f29e6f4516bd4ababcb3a7"},"schema_version":"1.0","source":{"id":"2506.19171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19171","created_at":"2026-07-05T11:26:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19171v1","created_at":"2026-07-05T11:26:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19171","created_at":"2026-07-05T11:26:10Z"},{"alias_kind":"pith_short_12","alias_value":"W2FFIX34FAAI","created_at":"2026-07-05T11:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"W2FFIX34FAAI2KKJ","created_at":"2026-07-05T11:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"W2FFIX34","created_at":"2026-07-05T11:26:10Z"}],"graph_snapshots":[{"event_id":"sha256:a3acdebafc44a2b2e21cb1ea144c8e2b28512941ddefdded0f940fb88818c44d","target":"graph","created_at":"2026-07-05T11:26:10Z","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/2506.19171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often struggle with mathematical problems that require exact computation or multi-step algebraic reasoning. Tool-integrated reasoning (TIR) offers a promising solution by leveraging external tools such as code interpreters to ensure correctness, but it introduces inference-time dependencies that hinder scalability and deployment. In this work, we propose a new paradigm for distilling tool knowledge into LLMs purely through natural language. We first construct a Solver Agent that solves math problems by interleaving planning, symbolic tool calls, and reflective reas","authors_text":"Bailan He, Changran Hu, Guohao Li, Haige Bo, Rishabh, Waleed Alzarooni, Wendong Fan, Xianglong Hu, Xingyue Huang, Yuan He, Zifeng Ding, Ziyu Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T22:10:38Z","title":"Distilling Tool Knowledge into Language Models via Back-Translated Traces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19171","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:cf2b726fe279748d13b31d1ee1b37f387ec806ab708fc0981469cf0dbd16b089","target":"record","created_at":"2026-07-05T11:26:10Z","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":"634dce81fce35264187f86f69fad09f8ec6810c4d5c19d5836e5857c0414de9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T22:10:38Z","title_canon_sha256":"e340b05055e10b6b4d46c28986db6f4f0d1827e3a7f29e6f4516bd4ababcb3a7"},"schema_version":"1.0","source":{"id":"2506.19171","kind":"arxiv","version":1}},"canonical_sha256":"b68a545f7c28008d2949ba1b13794383748db1159499aa6e850726d25d5bb32e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b68a545f7c28008d2949ba1b13794383748db1159499aa6e850726d25d5bb32e","first_computed_at":"2026-07-05T11:26:10.498451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:10.498451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jiBisSP4LDXZMTvaGjhgZw1pl/k0dVC+uN8xOpsyKMr/AO+/vwWdV4q2T4mi0/qQSmwHD+NcWea23EJCfl0gBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:10.499084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf2b726fe279748d13b31d1ee1b37f387ec806ab708fc0981469cf0dbd16b089","sha256:a3acdebafc44a2b2e21cb1ea144c8e2b28512941ddefdded0f940fb88818c44d"],"state_sha256":"d8c7a98399826e9fe903f00950ae1ce608bf0bfc691c4c0810a058cda7036375"}