{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VWK3CA33WAUD6XWYMQII7ABZMN","short_pith_number":"pith:VWK3CA33","schema_version":"1.0","canonical_sha256":"ad95b1037bb0283f5ed864108f8039635ea2351183e73110b70d6dbc31218cfd","source":{"kind":"arxiv","id":"2309.16573","version":2},"attestation_state":"computed","paper":{"title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.AI","authors_text":"Aleksandar Petrov, Anthony G. Cohn, Christoph Weinhuber, Emanuele La Malfa, Michael Wooldridge, Nigel Shadbolt, Raza Nazar, Ryan Burnell, Simon Frieder","submitted_at":"2023-09-28T16:29:52Z","abstract_excerpt":"Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the Language-Models-as-a-Service (LMaaS) paradigm. In contrast with scenarios where full model access is available, as in the case of open-source models, such closed-off language models present specific challenges for evaluating, benchmarking, and testing them. This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, replicability, reliability, and trustw"},"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":"2309.16573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-28T16:29:52Z","cross_cats_sorted":["cs.CL","cs.CY"],"title_canon_sha256":"b0ef8f7bbf802b202ca235a046adb30828686a08130ce67eacd6af064080af75","abstract_canon_sha256":"f05bd6cb11747c3acd32cc54c134f37746125a98945ebdb9223f6fe319604481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:30.015552Z","signature_b64":"VsXmDOC/hIz2zzL+HkGuFhK4Qd/m03+kBshX+FFd9qDcN7cX/tutmJUCDN/NS6UvjOJHUDigqKu4F5scX5lYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad95b1037bb0283f5ed864108f8039635ea2351183e73110b70d6dbc31218cfd","last_reissued_at":"2026-07-05T07:18:30.015066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:30.015066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.AI","authors_text":"Aleksandar Petrov, Anthony G. Cohn, Christoph Weinhuber, Emanuele La Malfa, Michael Wooldridge, Nigel Shadbolt, Raza Nazar, Ryan Burnell, Simon Frieder","submitted_at":"2023-09-28T16:29:52Z","abstract_excerpt":"Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the Language-Models-as-a-Service (LMaaS) paradigm. In contrast with scenarios where full model access is available, as in the case of open-source models, such closed-off language models present specific challenges for evaluating, benchmarking, and testing them. This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, replicability, reliability, and trustw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16573","kind":"arxiv","version":2},"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/2309.16573/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":"2309.16573","created_at":"2026-07-05T07:18:30.015126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16573v2","created_at":"2026-07-05T07:18:30.015126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16573","created_at":"2026-07-05T07:18:30.015126+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWK3CA33WAUD","created_at":"2026-07-05T07:18:30.015126+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWK3CA33WAUD6XWY","created_at":"2026-07-05T07:18:30.015126+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWK3CA33","created_at":"2026-07-05T07:18:30.015126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.09629","citing_title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01263","citing_title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":229,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN","json":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN.json","graph_json":"https://pith.science/api/pith-number/VWK3CA33WAUD6XWYMQII7ABZMN/graph.json","events_json":"https://pith.science/api/pith-number/VWK3CA33WAUD6XWYMQII7ABZMN/events.json","paper":"https://pith.science/paper/VWK3CA33"},"agent_actions":{"view_html":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN","download_json":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN.json","view_paper":"https://pith.science/paper/VWK3CA33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16573&json=true","fetch_graph":"https://pith.science/api/pith-number/VWK3CA33WAUD6XWYMQII7ABZMN/graph.json","fetch_events":"https://pith.science/api/pith-number/VWK3CA33WAUD6XWYMQII7ABZMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN/action/storage_attestation","attest_author":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN/action/author_attestation","sign_citation":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN/action/citation_signature","submit_replication":"https://pith.science/pith/VWK3CA33WAUD6XWYMQII7ABZMN/action/replication_record"}},"created_at":"2026-07-05T07:18:30.015126+00:00","updated_at":"2026-07-05T07:18:30.015126+00:00"}