{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6COEPFP6XQJDASQ2SCLRAYQTBI","short_pith_number":"pith:6COEPFP6","schema_version":"1.0","canonical_sha256":"f09c4795febc12304a1a90971062130a09e546f90aef3f97bd3e1e45cd48f6b3","source":{"kind":"arxiv","id":"2404.01549","version":1},"attestation_state":"computed","paper":{"title":"Octopus: On-device language model for function calling of software APIs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Mingyuan Ma, Wei Chen, Zhiyuan Li","submitted_at":"2024-04-02T01:29:28Z","abstract_excerpt":"In the rapidly evolving domain of artificial intelligence, Large Language Models (LLMs) play a crucial role due to their advanced text processing and generation abilities. This study introduces a new strategy aimed at harnessing on-device LLMs in invoking software APIs. We meticulously compile a dataset derived from software API documentation and apply fine-tuning to LLMs with capacities of 2B, 3B and 7B parameters, specifically to enhance their proficiency in software API interactions. Our approach concentrates on refining the models' grasp of API structures and syntax, significantly enhancin"},"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":"2404.01549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T01:29:28Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"a2aca6bad1c2f5efc2b90bd86cce5e3ebb055813bd2dfe6906669913188a188d","abstract_canon_sha256":"bef00448c7d2c5d7de2b7c3b4dc66872c5946294444d3589a3cd2fb6b17fb742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:15.690767Z","signature_b64":"EHo16lKlSj5ZzI7hNXxJErKdqGuABBb230h6U39VCO2uvnkfrsetMbCHzRSfFSwxfL6BERUlolgZpw7tiQKhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f09c4795febc12304a1a90971062130a09e546f90aef3f97bd3e1e45cd48f6b3","last_reissued_at":"2026-07-05T08:03:15.690294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:15.690294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Octopus: On-device language model for function calling of software APIs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Mingyuan Ma, Wei Chen, Zhiyuan Li","submitted_at":"2024-04-02T01:29:28Z","abstract_excerpt":"In the rapidly evolving domain of artificial intelligence, Large Language Models (LLMs) play a crucial role due to their advanced text processing and generation abilities. This study introduces a new strategy aimed at harnessing on-device LLMs in invoking software APIs. We meticulously compile a dataset derived from software API documentation and apply fine-tuning to LLMs with capacities of 2B, 3B and 7B parameters, specifically to enhance their proficiency in software API interactions. Our approach concentrates on refining the models' grasp of API structures and syntax, significantly enhancin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01549","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/2404.01549/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":"2404.01549","created_at":"2026-07-05T08:03:15.690358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01549v1","created_at":"2026-07-05T08:03:15.690358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01549","created_at":"2026-07-05T08:03:15.690358+00:00"},{"alias_kind":"pith_short_12","alias_value":"6COEPFP6XQJD","created_at":"2026-07-05T08:03:15.690358+00:00"},{"alias_kind":"pith_short_16","alias_value":"6COEPFP6XQJDASQ2","created_at":"2026-07-05T08:03:15.690358+00:00"},{"alias_kind":"pith_short_8","alias_value":"6COEPFP6","created_at":"2026-07-05T08:03:15.690358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.14703","citing_title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI","json":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI.json","graph_json":"https://pith.science/api/pith-number/6COEPFP6XQJDASQ2SCLRAYQTBI/graph.json","events_json":"https://pith.science/api/pith-number/6COEPFP6XQJDASQ2SCLRAYQTBI/events.json","paper":"https://pith.science/paper/6COEPFP6"},"agent_actions":{"view_html":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI","download_json":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI.json","view_paper":"https://pith.science/paper/6COEPFP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01549&json=true","fetch_graph":"https://pith.science/api/pith-number/6COEPFP6XQJDASQ2SCLRAYQTBI/graph.json","fetch_events":"https://pith.science/api/pith-number/6COEPFP6XQJDASQ2SCLRAYQTBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI/action/storage_attestation","attest_author":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI/action/author_attestation","sign_citation":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI/action/citation_signature","submit_replication":"https://pith.science/pith/6COEPFP6XQJDASQ2SCLRAYQTBI/action/replication_record"}},"created_at":"2026-07-05T08:03:15.690358+00:00","updated_at":"2026-07-05T08:03:15.690358+00:00"}