{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X7HO3CBICBSQEPQM57ZZSVNULD","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":"96595435051b509bd7b7b3a946be4f05a686d232f8af432977c3639d242710c4","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T16:39:19Z","title_canon_sha256":"612c6d62009d81f082693a7684b1ed10dcb31301e29f1f88ac87a5bf456af25b"},"schema_version":"1.0","source":{"id":"2502.14893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14893","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14893v1","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14893","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"pith_short_12","alias_value":"X7HO3CBICBSQ","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"pith_short_16","alias_value":"X7HO3CBICBSQEPQM","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"pith_short_8","alias_value":"X7HO3CBI","created_at":"2026-07-05T10:17:36Z"}],"graph_snapshots":[{"event_id":"sha256:4e7e5d938d0720bb96c058bbc7b358767742c61ff7e03873ab91788cd485a54a","target":"graph","created_at":"2026-07-05T10:17:36Z","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/2502.14893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol sequence text. Existing general-domain visual language models still lack the ability of music notation understanding. Recognizing this gap, we propose NOTA, the first large-scale comprehensive multimodal music notation dataset. It consists of 1,019,237 records, from 3 regions of the world, and contains 3","authors_text":"Jiajia Li, Jinghao Tian, Lefei Zhang, Lu Yang, Mingni Tang, Ping Wang, Zhiqiang Zhang, Zuchao Li","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T16:39:19Z","title":"NOTA: Multimodal Music Notation Understanding for Visual Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14893","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:bf7ab91b88bf7448adecf2bb014de36fd00ec5598e6c60b3a86b3b24b321a3a7","target":"record","created_at":"2026-07-05T10:17:36Z","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":"96595435051b509bd7b7b3a946be4f05a686d232f8af432977c3639d242710c4","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T16:39:19Z","title_canon_sha256":"612c6d62009d81f082693a7684b1ed10dcb31301e29f1f88ac87a5bf456af25b"},"schema_version":"1.0","source":{"id":"2502.14893","kind":"arxiv","version":1}},"canonical_sha256":"bfceed88281065023e0ceff39955b458eae33733f8a551ce02f1e2e14642de12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfceed88281065023e0ceff39955b458eae33733f8a551ce02f1e2e14642de12","first_computed_at":"2026-07-05T10:17:36.057463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:36.057463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iR61nfa7ntPkCQH8Isf1x3Szs8Uqeiu7HoI8yWUGX6WYsEqLo4Y7lrdm4Yqki/b9qDdEhNgToVA8I7L2pQ6pDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:36.057933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf7ab91b88bf7448adecf2bb014de36fd00ec5598e6c60b3a86b3b24b321a3a7","sha256:4e7e5d938d0720bb96c058bbc7b358767742c61ff7e03873ab91788cd485a54a"],"state_sha256":"046ce9cd6670bdac573fb981f94080f2067cd261689704d97d90168ce1f9036e"}