{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5GEXQBUVTLQ6FKBSG27NVFWKBS","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":"189f831bf89c98eb3f7d75fd268058fd18333a33362796a72ba32dd4f7000b3c","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T17:41:57Z","title_canon_sha256":"ef0edde39bda47728ed60a5f08a919731d29463cf2cfcecd9967a186dabff5a2"},"schema_version":"1.0","source":{"id":"2502.06710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06710","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06710v1","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06710","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"5GEXQBUVTLQ6","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"5GEXQBUVTLQ6FKBS","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"5GEXQBUV","created_at":"2026-07-05T10:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:f2fbf9f2f00d3fa915a43e46e105b69f3a701f64f127c1b725246993889da136","target":"graph","created_at":"2026-07-05T10:12:11Z","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/2502.06710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music performances are representative scenarios for audio-visual modeling. Unlike common scenarios with sparse audio, music performances continuously involve dense audio signals throughout. While existing multimodal learning methods on the audio-video QA demonstrate impressive capabilities in general scenarios, they are incapable of dealing with fundamental problems within the music performances: they underexplore the interaction between the multimodal signals in performance and fail to consider the distinctive characteristics of instruments and music. Therefore, existing methods tend to answe","authors_text":"Chunhui Zhang, Jiang Gui, Ming Cheng, Tingxuan Wu, Weiyi Wu, Xingjian Diao, Zhongyu Ouyang","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T17:41:57Z","title":"Learning Musical Representations for Music Performance Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06710","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":"sha256:719bb7c9347bb4e0d844bf2c2f7479b734552883fd13fc1b2acf8ffd5fb695b4","target":"record","created_at":"2026-07-05T10:12:11Z","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":"189f831bf89c98eb3f7d75fd268058fd18333a33362796a72ba32dd4f7000b3c","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T17:41:57Z","title_canon_sha256":"ef0edde39bda47728ed60a5f08a919731d29463cf2cfcecd9967a186dabff5a2"},"schema_version":"1.0","source":{"id":"2502.06710","kind":"arxiv","version":1}},"canonical_sha256":"e9897806959ae1e2a83236beda96ca0c85141f8051858bd850e4b11a24cfb46f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9897806959ae1e2a83236beda96ca0c85141f8051858bd850e4b11a24cfb46f","first_computed_at":"2026-07-05T10:12:11.225023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:11.225023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SkyhkgnJHq3rnjXNPI4CZraQkpoNvB+uzie7X65MFsLGQyP62J2XNc3v4qW57/8F/yguXazjpuNf2HgWid7+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:11.225501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:719bb7c9347bb4e0d844bf2c2f7479b734552883fd13fc1b2acf8ffd5fb695b4","sha256:f2fbf9f2f00d3fa915a43e46e105b69f3a701f64f127c1b725246993889da136"],"state_sha256":"c282eff22b4b2f74e59d3985fafac02ff8965328038c8fab2e818b4c8957f498"}