{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V2DPJ5HORX72XQB66CTCL2UPWS","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":"7094151c726ee880b20b674e159293f2c2421d5c86b2601441409070d051a688","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T22:41:38Z","title_canon_sha256":"e4a2faae3466e6c180ff6dd868e2722d48af54d5dc3364ea2bc65c677e041994"},"schema_version":"1.0","source":{"id":"2402.14158","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14158","created_at":"2026-07-05T07:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14158v2","created_at":"2026-07-05T07:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14158","created_at":"2026-07-05T07:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"V2DPJ5HORX72","created_at":"2026-07-05T07:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"V2DPJ5HORX72XQB6","created_at":"2026-07-05T07:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"V2DPJ5HO","created_at":"2026-07-05T07:55:28Z"}],"graph_snapshots":[{"event_id":"sha256:f45a72a07091aaa5c67fa70d9ae2eb51a98d40dd548ad970f82fe4f459d6ee0c","target":"graph","created_at":"2026-07-05T07:55:28Z","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/2402.14158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learning to use specific tools via fine-tuning, language models still struggle with learning how to robustly use new tools from only a few demonstrations. In this work we introduce a self-verification method which distinguishes between close candidates by self-asking contrastive questions during (1) tool selection; and (2) parameter generation. We construct synthetic, high-quality, self-generated data for this goal using ","authors_text":"Dheeraj Mekala, Jack Lanchantin, Jane Dwivedi-Yu, Jason Weston, Jingbo Shang, Maria Lomeli, Roberta Raileanu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T22:41:38Z","title":"TOOLVERIFIER: Generalization to New Tools via Self-Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14158","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:dfec6c867e5c5c68d8216aee150a5d051dc812bbf21a7f07dd8a575fa5a413e4","target":"record","created_at":"2026-07-05T07:55:28Z","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":"7094151c726ee880b20b674e159293f2c2421d5c86b2601441409070d051a688","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T22:41:38Z","title_canon_sha256":"e4a2faae3466e6c180ff6dd868e2722d48af54d5dc3364ea2bc65c677e041994"},"schema_version":"1.0","source":{"id":"2402.14158","kind":"arxiv","version":2}},"canonical_sha256":"ae86f4f4ee8dffabc03ef0a625ea8fb483bb085c8d4b082c60208021cfe4879e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae86f4f4ee8dffabc03ef0a625ea8fb483bb085c8d4b082c60208021cfe4879e","first_computed_at":"2026-07-05T07:55:28.640210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:28.640210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZejtJCl/HpuIYnmZ4lobgGnAdpI0vpISjFO8omiFoJ3M1hSGZEQ/QGKRxUPDDnHz2Hi9W0VD6Crm+3lqlAOLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:28.640819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14158","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfec6c867e5c5c68d8216aee150a5d051dc812bbf21a7f07dd8a575fa5a413e4","sha256:f45a72a07091aaa5c67fa70d9ae2eb51a98d40dd548ad970f82fe4f459d6ee0c"],"state_sha256":"4c9c2d7df022fd966ee97fb9a8dd46ee6c8cd6be4de7b4b6c98c326f28174eef"}