{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZSBC4RXOV6LFCNPBKVJA2VRMOC","short_pith_number":"pith:ZSBC4RXO","schema_version":"1.0","canonical_sha256":"cc822e46eeaf965135e155520d562c70910b523c5ea6a3d3425dd277d018b682","source":{"kind":"arxiv","id":"2606.18508","version":1},"attestation_state":"computed","paper":{"title":"MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Amirhossein Abaskohi, Gaetano Cimino, Giuseppe Carenini, Issam H. Laradji, Peter West, Raymond Li","submitted_at":"2026-06-16T21:50:01Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larger chunks reduce the number of candidates but make dense similarity less reliable, as the representation for each chunk mixes multiple topics and introduces more semantic noise. This trade-off becomes especially limiting in deep research tasks, where retrieval must be both fast and precise across large, heterogeneous corpora. We introduce MCompassRAG, a metadata-guided retrieva"},"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":"2606.18508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T21:50:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"887feafe9a7b3e4f9b275cbf8de5343f7f258abc8f4ae34c55c96bd6879c41dd","abstract_canon_sha256":"25f53ed5fb35b2b0321e603d0330cbff673961361434fcd86ab83ab8caf345d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:39.109997Z","signature_b64":"6TggCNSGRJVmqLTXZuvhoeaa/5M/R1ANN+7VBqu0ydxAaX5+bSPMDRQx59jZdO7JtyAyb2tXclh8pV2W/P8VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc822e46eeaf965135e155520d562c70910b523c5ea6a3d3425dd277d018b682","last_reissued_at":"2026-06-19T16:11:39.109645Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:39.109645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Amirhossein Abaskohi, Gaetano Cimino, Giuseppe Carenini, Issam H. Laradji, Peter West, Raymond Li","submitted_at":"2026-06-16T21:50:01Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larger chunks reduce the number of candidates but make dense similarity less reliable, as the representation for each chunk mixes multiple topics and introduces more semantic noise. This trade-off becomes especially limiting in deep research tasks, where retrieval must be both fast and precise across large, heterogeneous corpora. We introduce MCompassRAG, a metadata-guided retrieva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18508","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/2606.18508/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":"2606.18508","created_at":"2026-06-19T16:11:39.109711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18508v1","created_at":"2026-06-19T16:11:39.109711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18508","created_at":"2026-06-19T16:11:39.109711+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSBC4RXOV6LF","created_at":"2026-06-19T16:11:39.109711+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSBC4RXOV6LFCNPB","created_at":"2026-06-19T16:11:39.109711+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSBC4RXO","created_at":"2026-06-19T16:11:39.109711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC","json":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC.json","graph_json":"https://pith.science/api/pith-number/ZSBC4RXOV6LFCNPBKVJA2VRMOC/graph.json","events_json":"https://pith.science/api/pith-number/ZSBC4RXOV6LFCNPBKVJA2VRMOC/events.json","paper":"https://pith.science/paper/ZSBC4RXO"},"agent_actions":{"view_html":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC","download_json":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC.json","view_paper":"https://pith.science/paper/ZSBC4RXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18508&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSBC4RXOV6LFCNPBKVJA2VRMOC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSBC4RXOV6LFCNPBKVJA2VRMOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC/action/storage_attestation","attest_author":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC/action/author_attestation","sign_citation":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC/action/citation_signature","submit_replication":"https://pith.science/pith/ZSBC4RXOV6LFCNPBKVJA2VRMOC/action/replication_record"}},"created_at":"2026-06-19T16:11:39.109711+00:00","updated_at":"2026-06-19T16:11:39.109711+00:00"}