{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6O75W2XMAYYBQEN3EI22H3KYTF","short_pith_number":"pith:6O75W2XM","canonical_record":{"source":{"id":"2409.15523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-23T20:16:49Z","cross_cats_sorted":[],"title_canon_sha256":"9b055fb364c4d25d8baf2b2987a621a2fd9725ecb5f137f12bd76b64627f8e69","abstract_canon_sha256":"f222e05bd785c7f8e59867f7be505b13c2df7f2259bddc34a33f74a8dbffed47"},"schema_version":"1.0"},"canonical_sha256":"f3bfdb6aec06301811bb2235a3ed5899712428b2c773167d17a13d312b0f498a","source":{"kind":"arxiv","id":"2409.15523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15523","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15523v1","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15523","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"6O75W2XMAYYB","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"6O75W2XMAYYBQEN3","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"6O75W2XM","created_at":"2026-07-05T09:10:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6O75W2XMAYYBQEN3EI22H3KYTF","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-23T20:16:49Z","cross_cats_sorted":[],"title_canon_sha256":"9b055fb364c4d25d8baf2b2987a621a2fd9725ecb5f137f12bd76b64627f8e69","abstract_canon_sha256":"f222e05bd785c7f8e59867f7be505b13c2df7f2259bddc34a33f74a8dbffed47"},"schema_version":"1.0"},"canonical_sha256":"f3bfdb6aec06301811bb2235a3ed5899712428b2c773167d17a13d312b0f498a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:56.236934Z","signature_b64":"NM9aCKDFuw/NejnskIm9B+//GX3EwDY6mANElGwqklGwdZYQ3FqsLL1J6QexEhbSxC4bPQ93RPX+wto4HZiKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3bfdb6aec06301811bb2235a3ed5899712428b2c773167d17a13d312b0f498a","last_reissued_at":"2026-07-05T09:10:56.236476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:56.236476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15523","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oanFZqhNtpXzjcV+p1Gu9cdipXbW9K/dS9R5zst5BCET5nnl30Vpm8d2yiwhj8vsXkRYnls9e9lEdZoRyxvtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:18:35.639926Z"},"content_sha256":"aab0174edf2b7617c772d9b0c19aa57246938a59c8b2efb5cad38e8d671c4f49","schema_version":"1.0","event_id":"sha256:aab0174edf2b7617c772d9b0c19aa57246938a59c8b2efb5cad38e8d671c4f49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6O75W2XMAYYBQEN3EI22H3KYTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEAL: Suite for Evaluating API-use of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aditya Vempaty, Ashish Jagmohan, Woojeong Kim","submitted_at":"2024-09-23T20:16:49Z","abstract_excerpt":"Large language models (LLMs) have limitations in handling tasks that require real-time access to external APIs. While several benchmarks like ToolBench and APIGen have been developed to assess LLMs' API-use capabilities, they often suffer from issues such as lack of generalizability, limited multi-step reasoning coverage, and instability due to real-time API fluctuations. In this paper, we introduce SEAL, an end-to-end testbed designed to evaluate LLMs in real-world API usage. SEAL standardizes existing benchmarks, integrates an agent system for testing API retrieval and planning, and addresse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15523","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/2409.15523/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znmNgXCOkLvwt7Cw1TDicBE+ILSfiDMiKTFRTEXOfUKY43bgb0g40J9UcSU2tSq3Gj2cCchSKLAfQKs4ezC3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:18:35.640458Z"},"content_sha256":"2c8e500d6adcb4a170261036377ca98f9ab35087401aaf062f47c8ce8a486274","schema_version":"1.0","event_id":"sha256:2c8e500d6adcb4a170261036377ca98f9ab35087401aaf062f47c8ce8a486274"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6O75W2XMAYYBQEN3EI22H3KYTF/bundle.json","state_url":"https://pith.science/pith/6O75W2XMAYYBQEN3EI22H3KYTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6O75W2XMAYYBQEN3EI22H3KYTF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T15:18:35Z","links":{"resolver":"https://pith.science/pith/6O75W2XMAYYBQEN3EI22H3KYTF","bundle":"https://pith.science/pith/6O75W2XMAYYBQEN3EI22H3KYTF/bundle.json","state":"https://pith.science/pith/6O75W2XMAYYBQEN3EI22H3KYTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6O75W2XMAYYBQEN3EI22H3KYTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6O75W2XMAYYBQEN3EI22H3KYTF","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":"f222e05bd785c7f8e59867f7be505b13c2df7f2259bddc34a33f74a8dbffed47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-23T20:16:49Z","title_canon_sha256":"9b055fb364c4d25d8baf2b2987a621a2fd9725ecb5f137f12bd76b64627f8e69"},"schema_version":"1.0","source":{"id":"2409.15523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15523","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15523v1","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15523","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"6O75W2XMAYYB","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"6O75W2XMAYYBQEN3","created_at":"2026-07-05T09:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"6O75W2XM","created_at":"2026-07-05T09:10:56Z"}],"graph_snapshots":[{"event_id":"sha256:2c8e500d6adcb4a170261036377ca98f9ab35087401aaf062f47c8ce8a486274","target":"graph","created_at":"2026-07-05T09:10:56Z","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/2409.15523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have limitations in handling tasks that require real-time access to external APIs. While several benchmarks like ToolBench and APIGen have been developed to assess LLMs' API-use capabilities, they often suffer from issues such as lack of generalizability, limited multi-step reasoning coverage, and instability due to real-time API fluctuations. In this paper, we introduce SEAL, an end-to-end testbed designed to evaluate LLMs in real-world API usage. SEAL standardizes existing benchmarks, integrates an agent system for testing API retrieval and planning, and addresse","authors_text":"Aditya Vempaty, Ashish Jagmohan, Woojeong Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-23T20:16:49Z","title":"SEAL: Suite for Evaluating API-use of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15523","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:aab0174edf2b7617c772d9b0c19aa57246938a59c8b2efb5cad38e8d671c4f49","target":"record","created_at":"2026-07-05T09:10:56Z","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":"f222e05bd785c7f8e59867f7be505b13c2df7f2259bddc34a33f74a8dbffed47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-23T20:16:49Z","title_canon_sha256":"9b055fb364c4d25d8baf2b2987a621a2fd9725ecb5f137f12bd76b64627f8e69"},"schema_version":"1.0","source":{"id":"2409.15523","kind":"arxiv","version":1}},"canonical_sha256":"f3bfdb6aec06301811bb2235a3ed5899712428b2c773167d17a13d312b0f498a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3bfdb6aec06301811bb2235a3ed5899712428b2c773167d17a13d312b0f498a","first_computed_at":"2026-07-05T09:10:56.236476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:56.236476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NM9aCKDFuw/NejnskIm9B+//GX3EwDY6mANElGwqklGwdZYQ3FqsLL1J6QexEhbSxC4bPQ93RPX+wto4HZiKBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:56.236934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aab0174edf2b7617c772d9b0c19aa57246938a59c8b2efb5cad38e8d671c4f49","sha256:2c8e500d6adcb4a170261036377ca98f9ab35087401aaf062f47c8ce8a486274"],"state_sha256":"ed61569eb450b9e3480d0a8cede2a779152ff05580228dc11704679988e57b04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqjZxBtOjkt5nxAbARMX+nEZoOsajWhamVYsyTCN9cFGUknJE4QrcAujI7hDyDhZqe3SuA+kCx3OrXo+UMl5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:18:35.644245Z","bundle_sha256":"2ec755689c7cb2d8efa768397c9d6f9bddede90c1fccf9750ed732d7e79f0007"}}