{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DQ62XXYNEE4ME3YAHIJTK6X3SU","short_pith_number":"pith:DQ62XXYN","schema_version":"1.0","canonical_sha256":"1c3dabdf0d2138c26f003a13357afb953ea6cb8918665c6e22fa1de0af456dcb","source":{"kind":"arxiv","id":"2606.08722","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Andrea Poltronieri, Antonio Rod\\`a, Matteo Spanio, Mohammad Torabi","submitted_at":"2026-06-07T16:32:59Z","abstract_excerpt":"Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointly evaluates symbolic music generation and music understanding on the same family of open-weight LLMs. The benchmark includes a 200-prompt generation suite and ten understanding tasks adapted from ABC-Eval, covering syntax, metadata prediction, structural sequencing, and music recognition. Generation quality is evaluated using compile rate, MusPy descriptor distributions via Jensen-Shannon similarity, and LilyBERT-bas"},"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":"2606.08722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-07T16:32:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b59eef23bb88bde8991a103838549513d8496240be15900954cee755c6047848","abstract_canon_sha256":"30619f426ef8d9d7aa732d642b2477ab66d30f5a9cfeed9154c23766866db1f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:35.379483Z","signature_b64":"YwDvf7PN6A6LgdPeAR5CbncNCwdm3ArOgcsnaMfsxgrDBmOWq08bR8aw5POzYSw/dTNyT1NXAKQPaIpKhvN7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c3dabdf0d2138c26f003a13357afb953ea6cb8918665c6e22fa1de0af456dcb","last_reissued_at":"2026-06-09T02:07:35.378799Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:35.378799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Andrea Poltronieri, Antonio Rod\\`a, Matteo Spanio, Mohammad Torabi","submitted_at":"2026-06-07T16:32:59Z","abstract_excerpt":"Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointly evaluates symbolic music generation and music understanding on the same family of open-weight LLMs. The benchmark includes a 200-prompt generation suite and ten understanding tasks adapted from ABC-Eval, covering syntax, metadata prediction, structural sequencing, and music recognition. Generation quality is evaluated using compile rate, MusPy descriptor distributions via Jensen-Shannon similarity, and LilyBERT-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08722","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/2606.08722/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":"2606.08722","created_at":"2026-06-09T02:07:35.378887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08722v1","created_at":"2026-06-09T02:07:35.378887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08722","created_at":"2026-06-09T02:07:35.378887+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQ62XXYNEE4M","created_at":"2026-06-09T02:07:35.378887+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQ62XXYNEE4ME3YA","created_at":"2026-06-09T02:07:35.378887+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQ62XXYN","created_at":"2026-06-09T02:07:35.378887+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/DQ62XXYNEE4ME3YAHIJTK6X3SU","json":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU.json","graph_json":"https://pith.science/api/pith-number/DQ62XXYNEE4ME3YAHIJTK6X3SU/graph.json","events_json":"https://pith.science/api/pith-number/DQ62XXYNEE4ME3YAHIJTK6X3SU/events.json","paper":"https://pith.science/paper/DQ62XXYN"},"agent_actions":{"view_html":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU","download_json":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU.json","view_paper":"https://pith.science/paper/DQ62XXYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08722&json=true","fetch_graph":"https://pith.science/api/pith-number/DQ62XXYNEE4ME3YAHIJTK6X3SU/graph.json","fetch_events":"https://pith.science/api/pith-number/DQ62XXYNEE4ME3YAHIJTK6X3SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU/action/storage_attestation","attest_author":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU/action/author_attestation","sign_citation":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU/action/citation_signature","submit_replication":"https://pith.science/pith/DQ62XXYNEE4ME3YAHIJTK6X3SU/action/replication_record"}},"created_at":"2026-06-09T02:07:35.378887+00:00","updated_at":"2026-06-09T02:07:35.378887+00:00"}