{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PPO23UC672IVIADRXZBSWOEJ4T","short_pith_number":"pith:PPO23UC6","schema_version":"1.0","canonical_sha256":"7bddadd05efe91540071be432b3889e4e16bd7fc97c24c26d935b9f559fd8a5e","source":{"kind":"arxiv","id":"2108.00573","version":3},"attestation_state":"computed","paper":{"title":"MuSiQue: Multihop Questions via Single-hop Question Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot","submitted_at":"2021-08-02T00:33:27Z","abstract_excerpt":"Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, \\emph{requires} proper multihop reasoning? To this end, we introduce a bottom-up approach that systematically selects composable pairs of single-hop questions that are connected, i.e., where one reasoning step critically relies on information from another. This bottom-up methodology lets us explore a vast space of questions and add stringent filters as well as other mechanisms targeting connected reason"},"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":"2108.00573","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T00:33:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"334dfa2cdbaccb508bfa95df403e7277f577a8391397c2b1e406d4d54624639e","abstract_canon_sha256":"3843a9495cfe6644a69427d14debafc08a974d0281418d3e716ebe48cba80d27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:28.977308Z","signature_b64":"DsdV7VLAzItU5EnEcjPlJoSg1cTpMMXGbtIbhmkkZ0rVYsaWwL3/P9k8UqrHwSjg4sG/cywxn1tpLOTzVZXJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bddadd05efe91540071be432b3889e4e16bd7fc97c24c26d935b9f559fd8a5e","last_reissued_at":"2026-07-05T04:20:28.976822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:28.976822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuSiQue: Multihop Questions via Single-hop Question Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot","submitted_at":"2021-08-02T00:33:27Z","abstract_excerpt":"Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, \\emph{requires} proper multihop reasoning? To this end, we introduce a bottom-up approach that systematically selects composable pairs of single-hop questions that are connected, i.e., where one reasoning step critically relies on information from another. This bottom-up methodology lets us explore a vast space of questions and add stringent filters as well as other mechanisms targeting connected reason"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00573","kind":"arxiv","version":3},"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/2108.00573/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":"2108.00573","created_at":"2026-07-05T04:20:28.976881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00573v3","created_at":"2026-07-05T04:20:28.976881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00573","created_at":"2026-07-05T04:20:28.976881+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPO23UC672IV","created_at":"2026-07-05T04:20:28.976881+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPO23UC672IVIADR","created_at":"2026-07-05T04:20:28.976881+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPO23UC6","created_at":"2026-07-05T04:20:28.976881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23581","citing_title":"Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18075","citing_title":"A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05901","citing_title":"Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05875","citing_title":"QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03022","citing_title":"Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29863","citing_title":"KbSD: Knowledge Boundary aware Self-Distillation for Behavioral Calibration in Agentic Search","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27361","citing_title":"Natural Language Query to Configuration for Retrieval Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14913","citing_title":"PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15156","citing_title":"MeMo: Memory as a Model","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09666","citing_title":"Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T","json":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T.json","graph_json":"https://pith.science/api/pith-number/PPO23UC672IVIADRXZBSWOEJ4T/graph.json","events_json":"https://pith.science/api/pith-number/PPO23UC672IVIADRXZBSWOEJ4T/events.json","paper":"https://pith.science/paper/PPO23UC6"},"agent_actions":{"view_html":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T","download_json":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T.json","view_paper":"https://pith.science/paper/PPO23UC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00573&json=true","fetch_graph":"https://pith.science/api/pith-number/PPO23UC672IVIADRXZBSWOEJ4T/graph.json","fetch_events":"https://pith.science/api/pith-number/PPO23UC672IVIADRXZBSWOEJ4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T/action/storage_attestation","attest_author":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T/action/author_attestation","sign_citation":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T/action/citation_signature","submit_replication":"https://pith.science/pith/PPO23UC672IVIADRXZBSWOEJ4T/action/replication_record"}},"created_at":"2026-07-05T04:20:28.976881+00:00","updated_at":"2026-07-05T04:20:28.976881+00:00"}