{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EOIDI3MUVEUOTB4HOOZ35DIZTQ","short_pith_number":"pith:EOIDI3MU","schema_version":"1.0","canonical_sha256":"2390346d94a928e9878773b3be8d199c16b5b8300003202a9283882354904d1d","source":{"kind":"arxiv","id":"2506.23139","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Chien-Sheng Wu, Kung-Hsiang Huang, Prafulla Kumar Choubey, Shilpa Bhagavath, Xiangyu Peng","submitted_at":"2025-06-29T08:34:59Z","abstract_excerpt":"We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents, meeting transcripts, Slack messages, GitHub, and URLs, which vary in structure and often contain human-to-human interactions. We build it using a synthetic data pipeline that simulates business workflows across product planning, development, and support stages, generating interconnected content with realistic noise and multi-hop questions with guaranteed gr"},"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":"2506.23139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T08:34:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32963c325934124af54c700ac4694b8815e7a33f38246b944cc84cb0d8916409","abstract_canon_sha256":"eac652e9b2a0971321c2554c53198ce21e8a6770d1876fa295b09701cf162d26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:16.465361Z","signature_b64":"GVKVHMlMWtgQ6LDcMnc4rcxMxd2rCJBaHVX+JzDVEnpwfj+MeGulBXTn/PQRC/qiit6lBdwcpKkaROnA84gHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2390346d94a928e9878773b3be8d199c16b5b8300003202a9283882354904d1d","last_reissued_at":"2026-07-05T11:29:16.464845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:16.464845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Chien-Sheng Wu, Kung-Hsiang Huang, Prafulla Kumar Choubey, Shilpa Bhagavath, Xiangyu Peng","submitted_at":"2025-06-29T08:34:59Z","abstract_excerpt":"We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents, meeting transcripts, Slack messages, GitHub, and URLs, which vary in structure and often contain human-to-human interactions. We build it using a synthetic data pipeline that simulates business workflows across product planning, development, and support stages, generating interconnected content with realistic noise and multi-hop questions with guaranteed gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23139","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/2506.23139/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":"2506.23139","created_at":"2026-07-05T11:29:16.464904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23139v1","created_at":"2026-07-05T11:29:16.464904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23139","created_at":"2026-07-05T11:29:16.464904+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOIDI3MUVEUO","created_at":"2026-07-05T11:29:16.464904+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOIDI3MUVEUOTB4H","created_at":"2026-07-05T11:29:16.464904+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOIDI3MU","created_at":"2026-07-05T11:29:16.464904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15505","citing_title":"X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15505","citing_title":"X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14259","citing_title":"Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ","json":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ.json","graph_json":"https://pith.science/api/pith-number/EOIDI3MUVEUOTB4HOOZ35DIZTQ/graph.json","events_json":"https://pith.science/api/pith-number/EOIDI3MUVEUOTB4HOOZ35DIZTQ/events.json","paper":"https://pith.science/paper/EOIDI3MU"},"agent_actions":{"view_html":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ","download_json":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ.json","view_paper":"https://pith.science/paper/EOIDI3MU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23139&json=true","fetch_graph":"https://pith.science/api/pith-number/EOIDI3MUVEUOTB4HOOZ35DIZTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EOIDI3MUVEUOTB4HOOZ35DIZTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ/action/storage_attestation","attest_author":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ/action/author_attestation","sign_citation":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ/action/citation_signature","submit_replication":"https://pith.science/pith/EOIDI3MUVEUOTB4HOOZ35DIZTQ/action/replication_record"}},"created_at":"2026-07-05T11:29:16.464904+00:00","updated_at":"2026-07-05T11:29:16.464904+00:00"}