{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5VZKF5CJZGLO45ZSPPSBRBSA4Y","short_pith_number":"pith:5VZKF5CJ","canonical_record":{"source":{"id":"2503.20527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T13:13:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b7bfb696fabfa02a110577154311cfd98cdd3cf7861e3e87c7335c788f2216e","abstract_canon_sha256":"69daa5522dfb70023645846238747295b910b272ea5d104aa361eff32067a7be"},"schema_version":"1.0"},"canonical_sha256":"ed72a2f449c996ee77327be4188640e621ea816f963ce0b12e58e0314368d8e4","source":{"kind":"arxiv","id":"2503.20527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20527","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20527v1","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20527","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"5VZKF5CJZGLO","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"5VZKF5CJZGLO45ZS","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"5VZKF5CJ","created_at":"2026-07-05T10:39:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5VZKF5CJZGLO45ZSPPSBRBSA4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2503.20527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T13:13:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b7bfb696fabfa02a110577154311cfd98cdd3cf7861e3e87c7335c788f2216e","abstract_canon_sha256":"69daa5522dfb70023645846238747295b910b272ea5d104aa361eff32067a7be"},"schema_version":"1.0"},"canonical_sha256":"ed72a2f449c996ee77327be4188640e621ea816f963ce0b12e58e0314368d8e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:39.665297Z","signature_b64":"7N76NmekSdErNUDYDbi0BWkwYhorft6h78cgW4p6Q6WuG2CsQkt6StlQria6jykdn0vR19+g62QFoGI4tdhOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed72a2f449c996ee77327be4188640e621ea816f963ce0b12e58e0314368d8e4","last_reissued_at":"2026-07-05T10:39:39.664776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:39.664776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.20527","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":"2026-07-05T10:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3fXmSGTRNw3gtlaXTG2dwSSzug6VGNF5r31apED0ncan7PBRwwqBP9dU2qhi0t7BHdmTGvImFDdrxEhD28CDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:59:54.206144Z"},"content_sha256":"0a952f21c9f444b036c0f649485e47b88745962765889acfd6836b7315d0da69","schema_version":"1.0","event_id":"sha256:0a952f21c9f444b036c0f649485e47b88745962765889acfd6836b7315d0da69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5VZKF5CJZGLO45ZSPPSBRBSA4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Wang, Sicheng Zhou, Sijie Cheng, Wenbing Huang, Yang Liu, Yuchen Niu, Zhicheng Guo","submitted_at":"2025-03-26T13:13:03Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. However, existing tool environments face challenges in balancing stability, scalability, and realness, particularly for benchmarking purposes. To address this problem, we propose MirrorAPI, a novel framework that trains specialized LLMs to accurately simulate real API responses, effectively acting as \"mirrors\" to tool environments. Using a comprehensive dataset of request-response pairs from 7,000+ APIs, we employ supervi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20527","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/2503.20527/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":"2026-07-05T10:39:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xw6K+kocmRxLjp1ldjEQ2RAL0vU5lOgftnDBXkpcZ1q6DiGq6ghsMAwdlXut+4kN4SfA9NK/7aPhg/GCBwTtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:59:54.206658Z"},"content_sha256":"b890f4b787364d94861342113d4743ec2f8da01515ddb116f22bceb92798e286","schema_version":"1.0","event_id":"sha256:b890f4b787364d94861342113d4743ec2f8da01515ddb116f22bceb92798e286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y/bundle.json","state_url":"https://pith.science/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y/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":"2026-08-08T16:59:54Z","links":{"resolver":"https://pith.science/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y","bundle":"https://pith.science/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y/bundle.json","state":"https://pith.science/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5VZKF5CJZGLO45ZSPPSBRBSA4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5VZKF5CJZGLO45ZSPPSBRBSA4Y","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":"69daa5522dfb70023645846238747295b910b272ea5d104aa361eff32067a7be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T13:13:03Z","title_canon_sha256":"4b7bfb696fabfa02a110577154311cfd98cdd3cf7861e3e87c7335c788f2216e"},"schema_version":"1.0","source":{"id":"2503.20527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20527","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20527v1","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20527","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"5VZKF5CJZGLO","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"5VZKF5CJZGLO45ZS","created_at":"2026-07-05T10:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"5VZKF5CJ","created_at":"2026-07-05T10:39:39Z"}],"graph_snapshots":[{"event_id":"sha256:b890f4b787364d94861342113d4743ec2f8da01515ddb116f22bceb92798e286","target":"graph","created_at":"2026-07-05T10:39:39Z","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/2503.20527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. However, existing tool environments face challenges in balancing stability, scalability, and realness, particularly for benchmarking purposes. To address this problem, we propose MirrorAPI, a novel framework that trains specialized LLMs to accurately simulate real API responses, effectively acting as \"mirrors\" to tool environments. Using a comprehensive dataset of request-response pairs from 7,000+ APIs, we employ supervi","authors_text":"Hao Wang, Sicheng Zhou, Sijie Cheng, Wenbing Huang, Yang Liu, Yuchen Niu, Zhicheng Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T13:13:03Z","title":"StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20527","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":"sha256:0a952f21c9f444b036c0f649485e47b88745962765889acfd6836b7315d0da69","target":"record","created_at":"2026-07-05T10:39:39Z","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":"69daa5522dfb70023645846238747295b910b272ea5d104aa361eff32067a7be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T13:13:03Z","title_canon_sha256":"4b7bfb696fabfa02a110577154311cfd98cdd3cf7861e3e87c7335c788f2216e"},"schema_version":"1.0","source":{"id":"2503.20527","kind":"arxiv","version":1}},"canonical_sha256":"ed72a2f449c996ee77327be4188640e621ea816f963ce0b12e58e0314368d8e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed72a2f449c996ee77327be4188640e621ea816f963ce0b12e58e0314368d8e4","first_computed_at":"2026-07-05T10:39:39.664776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:39.664776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7N76NmekSdErNUDYDbi0BWkwYhorft6h78cgW4p6Q6WuG2CsQkt6StlQria6jykdn0vR19+g62QFoGI4tdhOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:39.665297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a952f21c9f444b036c0f649485e47b88745962765889acfd6836b7315d0da69","sha256:b890f4b787364d94861342113d4743ec2f8da01515ddb116f22bceb92798e286"],"state_sha256":"b653488a139df6761de56e975ba6f7b53bd681acdc313194c24a7fe2d1bfd3bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYLtCVuuTkexg7zyxxLTzRhFa6CgWtqGw6leAzjiA8AY+QhRMKj0lMEVv2B1vFnmV5013Z7q3G01iBFeLSnrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:59:54.212570Z","bundle_sha256":"563247b90d1ca1aaea63fd9fecf2056ca8c9e64a52f1fbc3aa1eb15a5712a7c7"}}