{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:24TVKBNKFYHFYSQW64HS6ZJGGV","short_pith_number":"pith:24TVKBNK","schema_version":"1.0","canonical_sha256":"d7275505aa2e0e5c4a16f70f2f6526355e8e7a8492549a895eaf79d862a5d61c","source":{"kind":"arxiv","id":"2606.06284","version":1},"attestation_state":"computed","paper":{"title":"ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Laxmipriya Ganesh Iyer, Rahul Suresh Babu","submitted_at":"2026-06-04T15:24:10Z","abstract_excerpt":"Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step.\n  We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweig"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.06284","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T15:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"eba6023a4cbf2789113142dcaa90a194382cd3c4850ae7edd4140ff0cf852f71","abstract_canon_sha256":"8d81f013519a28d97fcdcd2f29a0a9c3fffbe550bf13c9d264b56faddabb4d61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:40.511113Z","signature_b64":"ypjxRm4JfUAyRXBMOZlMe0AOgiN9hDxEJKLq083rf7zJILIxdQcKLU5qnfqvuBlkciGzJdPxbAdY1Q3PdaOgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7275505aa2e0e5c4a16f70f2f6526355e8e7a8492549a895eaf79d862a5d61c","last_reissued_at":"2026-06-05T01:15:40.510741Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:40.510741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Laxmipriya Ganesh Iyer, Rahul Suresh Babu","submitted_at":"2026-06-04T15:24:10Z","abstract_excerpt":"Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step.\n  We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06284","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/2606.06284/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.06284","created_at":"2026-06-05T01:15:40.510801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06284v1","created_at":"2026-06-05T01:15:40.510801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06284","created_at":"2026-06-05T01:15:40.510801+00:00"},{"alias_kind":"pith_short_12","alias_value":"24TVKBNKFYHF","created_at":"2026-06-05T01:15:40.510801+00:00"},{"alias_kind":"pith_short_16","alias_value":"24TVKBNKFYHFYSQW","created_at":"2026-06-05T01:15:40.510801+00:00"},{"alias_kind":"pith_short_8","alias_value":"24TVKBNK","created_at":"2026-06-05T01:15:40.510801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV","json":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV.json","graph_json":"https://pith.science/api/pith-number/24TVKBNKFYHFYSQW64HS6ZJGGV/graph.json","events_json":"https://pith.science/api/pith-number/24TVKBNKFYHFYSQW64HS6ZJGGV/events.json","paper":"https://pith.science/paper/24TVKBNK"},"agent_actions":{"view_html":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV","download_json":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV.json","view_paper":"https://pith.science/paper/24TVKBNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06284&json=true","fetch_graph":"https://pith.science/api/pith-number/24TVKBNKFYHFYSQW64HS6ZJGGV/graph.json","fetch_events":"https://pith.science/api/pith-number/24TVKBNKFYHFYSQW64HS6ZJGGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV/action/storage_attestation","attest_author":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV/action/author_attestation","sign_citation":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV/action/citation_signature","submit_replication":"https://pith.science/pith/24TVKBNKFYHFYSQW64HS6ZJGGV/action/replication_record"}},"created_at":"2026-06-05T01:15:40.510801+00:00","updated_at":"2026-06-05T01:15:40.510801+00:00"}