{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TCTT2QETISC5APJSDIPKEO2MC","short_pith_number":"pith:3TCTT2QE","schema_version":"1.0","canonical_sha256":"dcc539ea049a242e81e990d0f511da60a0593841ffd75f4a6c64b7ccbd154607","source":{"kind":"arxiv","id":"2408.15002","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.IR","authors_text":"Elona Shatri, George Fazekas","submitted_at":"2024-08-27T12:34:41Z","abstract_excerpt":"Optical Music Recognition (OMR) automates the transcription of musical notation from images into machine-readable formats like MusicXML, MEI, or MIDI, significantly reducing the costs and time of manual transcription. This study explores knowledge discovery in OMR by applying instance segmentation using Mask R-CNN to enhance the detection and delineation of musical symbols in sheet music. Unlike Optical Character Recognition (OCR), OMR must handle the intricate semantics of Common Western Music Notation (CWMN), where symbol meanings depend on shape, position, and context. Our approach leverage"},"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":"2408.15002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-27T12:34:41Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"b8e33fc4f03218d8f0e70619ad89e7bff4c297668dc1a3dd2ed36df96f931aa7","abstract_canon_sha256":"41e7a26e8f02f02a14920f773424119eb6ec1a76205e1fc55275a5de48db889f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:31.271113Z","signature_b64":"rRMhbuGA1m8VFjBC2lrcztdIeXkXfG2/DP5AkBKjFYJzHFBKXLLHl+v+CU3z4IJKzlDCKf8CTxhzQUg9HzecCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcc539ea049a242e81e990d0f511da60a0593841ffd75f4a6c64b7ccbd154607","last_reissued_at":"2026-07-05T09:07:31.270549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:31.270549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.IR","authors_text":"Elona Shatri, George Fazekas","submitted_at":"2024-08-27T12:34:41Z","abstract_excerpt":"Optical Music Recognition (OMR) automates the transcription of musical notation from images into machine-readable formats like MusicXML, MEI, or MIDI, significantly reducing the costs and time of manual transcription. This study explores knowledge discovery in OMR by applying instance segmentation using Mask R-CNN to enhance the detection and delineation of musical symbols in sheet music. Unlike Optical Character Recognition (OCR), OMR must handle the intricate semantics of Common Western Music Notation (CWMN), where symbol meanings depend on shape, position, and context. Our approach leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15002","kind":"arxiv","version":2},"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/2408.15002/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":"2408.15002","created_at":"2026-07-05T09:07:31.270616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15002v2","created_at":"2026-07-05T09:07:31.270616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15002","created_at":"2026-07-05T09:07:31.270616+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TCTT2QETISC","created_at":"2026-07-05T09:07:31.270616+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TCTT2QETISC5APJ","created_at":"2026-07-05T09:07:31.270616+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TCTT2QE","created_at":"2026-07-05T09:07:31.270616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20719","citing_title":"ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC","json":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC.json","graph_json":"https://pith.science/api/pith-number/3TCTT2QETISC5APJSDIPKEO2MC/graph.json","events_json":"https://pith.science/api/pith-number/3TCTT2QETISC5APJSDIPKEO2MC/events.json","paper":"https://pith.science/paper/3TCTT2QE"},"agent_actions":{"view_html":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC","download_json":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC.json","view_paper":"https://pith.science/paper/3TCTT2QE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15002&json=true","fetch_graph":"https://pith.science/api/pith-number/3TCTT2QETISC5APJSDIPKEO2MC/graph.json","fetch_events":"https://pith.science/api/pith-number/3TCTT2QETISC5APJSDIPKEO2MC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC/action/storage_attestation","attest_author":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC/action/author_attestation","sign_citation":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC/action/citation_signature","submit_replication":"https://pith.science/pith/3TCTT2QETISC5APJSDIPKEO2MC/action/replication_record"}},"created_at":"2026-07-05T09:07:31.270616+00:00","updated_at":"2026-07-05T09:07:31.270616+00:00"}