{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDFKPE52RV6JZRG6HD3V3RANVP","short_pith_number":"pith:NDFKPE52","canonical_record":{"source":{"id":"2607.23722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T15:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"942dd601f5a3f8976e5af368845d7bcee21f1b58c73a1d8f801513595e2fb46d","abstract_canon_sha256":"65ad11901142434fba9690b8c6467404f24b12d898eb0629b77fcc4b4ddf028e"},"schema_version":"1.0"},"canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","source":{"kind":"arxiv","id":"2607.23722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23722","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23722v1","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23722","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"NDFKPE52RV6J","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"NDFKPE52RV6JZRG6","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"NDFKPE52","created_at":"2026-07-28T01:23:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDFKPE52RV6JZRG6HD3V3RANVP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T15:38:28Z","cross_cats_sorted":[],"title_canon_sha256":"942dd601f5a3f8976e5af368845d7bcee21f1b58c73a1d8f801513595e2fb46d","abstract_canon_sha256":"65ad11901142434fba9690b8c6467404f24b12d898eb0629b77fcc4b4ddf028e"},"schema_version":"1.0"},"canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:07.628504Z","signature_b64":"NZyLRrhL8dY4tPcL8UzswS5sbVgePpK/RKWcHSZrtKcjOx7IVRn14vIgCOW5QdNpQTRJV7UR9cRBYlJE6BWoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","last_reissued_at":"2026-07-28T01:23:07.627642Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:07.627642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23722","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":"2026-07-28T01:23:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBxKa0vmQNsOuYqm6atv0+WS/G83lSO/liI8cB9ePRNmQSOuQY4j1Po/7ucKADUCp62zRzRNeA9l6IjUPFrwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:12:45.211800Z"},"content_sha256":"4e9060a06944825b4324f8472cb7b784ecf163b935c4f7c7b25c1f76b2adcfaa","schema_version":"1.0","event_id":"sha256:4e9060a06944825b4324f8472cb7b784ecf163b935c4f7c7b25c1f76b2adcfaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDFKPE52RV6JZRG6HD3V3RANVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alphet Liu, Duran Zheng, Eileen Ye, Maxm Pan, Tianyuan Zou, Weihuang Zheng, Ya-Qin Zhang, Youyong Kong","submitted_at":"2026-07-26T15:38:28Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes. We refer to this capability as multi-step tool use. Existing benchmarks have advanced tool-use agent evaluation, but often focus on isolated API calls, short trajectories, or settings that are difficult to scale or control. We introduce E-Bench, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting. E-Bench de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23722","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/2607.23722/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":"2026-07-28T01:23:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VM3USYDtvrLPYfAM1EgdPvAGJEjYcbhsxilkGPqmJJYYphw0i1pAcMSFLuPrN7dghY9YJiIprehPYYmKN4ENDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:12:45.215293Z"},"content_sha256":"e02a3a7464644479c94191eeb21ea913fd9bfd8b2d0b402c8a2e523aabc31ae8","schema_version":"1.0","event_id":"sha256:e02a3a7464644479c94191eeb21ea913fd9bfd8b2d0b402c8a2e523aabc31ae8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/bundle.json","state_url":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDFKPE52RV6JZRG6HD3V3RANVP/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":"2026-08-05T12:12:45Z","links":{"resolver":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP","bundle":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/bundle.json","state":"https://pith.science/pith/NDFKPE52RV6JZRG6HD3V3RANVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDFKPE52RV6JZRG6HD3V3RANVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDFKPE52RV6JZRG6HD3V3RANVP","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":"65ad11901142434fba9690b8c6467404f24b12d898eb0629b77fcc4b4ddf028e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T15:38:28Z","title_canon_sha256":"942dd601f5a3f8976e5af368845d7bcee21f1b58c73a1d8f801513595e2fb46d"},"schema_version":"1.0","source":{"id":"2607.23722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23722","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23722v1","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23722","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"NDFKPE52RV6J","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"NDFKPE52RV6JZRG6","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"NDFKPE52","created_at":"2026-07-28T01:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:e02a3a7464644479c94191eeb21ea913fd9bfd8b2d0b402c8a2e523aabc31ae8","target":"graph","created_at":"2026-07-28T01:23:07Z","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/2607.23722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes. We refer to this capability as multi-step tool use. Existing benchmarks have advanced tool-use agent evaluation, but often focus on isolated API calls, short trajectories, or settings that are difficult to scale or control. We introduce E-Bench, a fully synthetic benchmark with 323 state-changing tasks across three product domains: Honor of Kings, QQ Music, and Tencent Meeting. E-Bench de","authors_text":"Alphet Liu, Duran Zheng, Eileen Ye, Maxm Pan, Tianyuan Zou, Weihuang Zheng, Ya-Qin Zhang, Youyong Kong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T15:38:28Z","title":"E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23722","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":"sha256:4e9060a06944825b4324f8472cb7b784ecf163b935c4f7c7b25c1f76b2adcfaa","target":"record","created_at":"2026-07-28T01:23:07Z","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":"65ad11901142434fba9690b8c6467404f24b12d898eb0629b77fcc4b4ddf028e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-26T15:38:28Z","title_canon_sha256":"942dd601f5a3f8976e5af368845d7bcee21f1b58c73a1d8f801513595e2fb46d"},"schema_version":"1.0","source":{"id":"2607.23722","kind":"arxiv","version":1}},"canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68caa793ba8d7c9cc4de38f75dc40dabc65a0d7107def69853cca9aeb7e61062","first_computed_at":"2026-07-28T01:23:07.627642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:07.627642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZyLRrhL8dY4tPcL8UzswS5sbVgePpK/RKWcHSZrtKcjOx7IVRn14vIgCOW5QdNpQTRJV7UR9cRBYlJE6BWoAg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:07.628504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e9060a06944825b4324f8472cb7b784ecf163b935c4f7c7b25c1f76b2adcfaa","sha256:e02a3a7464644479c94191eeb21ea913fd9bfd8b2d0b402c8a2e523aabc31ae8"],"state_sha256":"5cbb9bb87abd9eb4d576bcb8c47563680196556dd18ffde18206a570f7b58c9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUaHP2g40noFLp7090p8ShcA5qSW/Za/dN5T8KNbMMFukObvWGaFdpc26bRX8WXnxSgjAOlImLZ4cQNUw69qBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:12:45.230926Z","bundle_sha256":"c3b2a29db984bbcefd93cf39d4a5bff264cdfbf14074fa760afd2c87b5fa0be0"}}