{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WUDE36R25K45DQXCXSZYZKBC2D","short_pith_number":"pith:WUDE36R2","schema_version":"1.0","canonical_sha256":"b5064dfa3aeab9d1c2e2bcb38ca822d0d6e0a9f6316e74c7a5f8b16444f0e8fe","source":{"kind":"arxiv","id":"2501.07474","version":1},"attestation_state":"computed","paper":{"title":"Estimating Musical Surprisal in Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Giorgia Cantisani, Mathias Rose Bjare, Stefan Lattner","submitted_at":"2025-01-13T16:46:45Z","abstract_excerpt":"In modeling musical surprisal expectancy with computational methods, it has been proposed to use the information content (IC) of one-step predictions from an autoregressive model as a proxy for surprisal in symbolic music. With an appropriately chosen model, the IC of musical events has been shown to correlate with human perception of surprise and complexity aspects, including tonal and rhythmic complexity. This work investigates whether an analogous methodology can be applied to music audio. We train an autoregressive Transformer model to predict compressed latent audio representations of a p"},"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":"2501.07474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-13T16:46:45Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"e688c13c5993e85d624b7c29e255693c9c9eb1c3d1f0488b12cfbc397c942d35","abstract_canon_sha256":"3a59a8e8ba0b6df619a57dbcb3d78cadad743316109900184e3177c678c3da96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:28.936791Z","signature_b64":"zhiVUiuk/vd7T04v7Hlqa4MdNR1THOgo6U7+gN/gNdZUO43dn+zdTm4HCoPaF4uAAAIvHzCTSr01ypsj0umZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5064dfa3aeab9d1c2e2bcb38ca822d0d6e0a9f6316e74c7a5f8b16444f0e8fe","last_reissued_at":"2026-07-05T10:00:28.936325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:28.936325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating Musical Surprisal in Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Giorgia Cantisani, Mathias Rose Bjare, Stefan Lattner","submitted_at":"2025-01-13T16:46:45Z","abstract_excerpt":"In modeling musical surprisal expectancy with computational methods, it has been proposed to use the information content (IC) of one-step predictions from an autoregressive model as a proxy for surprisal in symbolic music. With an appropriately chosen model, the IC of musical events has been shown to correlate with human perception of surprise and complexity aspects, including tonal and rhythmic complexity. This work investigates whether an analogous methodology can be applied to music audio. We train an autoregressive Transformer model to predict compressed latent audio representations of a p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07474","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/2501.07474/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":"2501.07474","created_at":"2026-07-05T10:00:28.936381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07474v1","created_at":"2026-07-05T10:00:28.936381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07474","created_at":"2026-07-05T10:00:28.936381+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUDE36R25K45","created_at":"2026-07-05T10:00:28.936381+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUDE36R25K45DQXC","created_at":"2026-07-05T10:00:28.936381+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUDE36R2","created_at":"2026-07-05T10:00:28.936381+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/WUDE36R25K45DQXCXSZYZKBC2D","json":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D.json","graph_json":"https://pith.science/api/pith-number/WUDE36R25K45DQXCXSZYZKBC2D/graph.json","events_json":"https://pith.science/api/pith-number/WUDE36R25K45DQXCXSZYZKBC2D/events.json","paper":"https://pith.science/paper/WUDE36R2"},"agent_actions":{"view_html":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D","download_json":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D.json","view_paper":"https://pith.science/paper/WUDE36R2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07474&json=true","fetch_graph":"https://pith.science/api/pith-number/WUDE36R25K45DQXCXSZYZKBC2D/graph.json","fetch_events":"https://pith.science/api/pith-number/WUDE36R25K45DQXCXSZYZKBC2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D/action/storage_attestation","attest_author":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D/action/author_attestation","sign_citation":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D/action/citation_signature","submit_replication":"https://pith.science/pith/WUDE36R25K45DQXCXSZYZKBC2D/action/replication_record"}},"created_at":"2026-07-05T10:00:28.936381+00:00","updated_at":"2026-07-05T10:00:28.936381+00:00"}