{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P4LG6Z5P7GBTKXOOIIEDX5VX6Z","short_pith_number":"pith:P4LG6Z5P","schema_version":"1.0","canonical_sha256":"7f166f67aff983355dce42083bf6b7f655bfadeff004142380ace07e01d0e366","source":{"kind":"arxiv","id":"2607.10003","version":1},"attestation_state":"computed","paper":{"title":"ARIMA: Reconstruction-Grounded Predictive Representation Learning for Symbolic Music","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Mingyang Yao, Zhaoxiang Feng","submitted_at":"2026-07-10T22:02:00Z","abstract_excerpt":"Self-supervised learning for symbolic music has advanced largely through token-level pretraining, but such representations remain tied to tokenizer-specific sequences and often provide time-span-level embeddings only indirectly. In this paper, we propose ARIMA, a reconstruction-grounded latent predictive framework for symbolic music that learns compact window-based representations directly from data. ARIMA encodes each fixed-duration window into a continuous latent representation, trains a causal predictor with contrastive next-latent prediction, and grounds the encoder through structured reco"},"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":"2607.10003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-10T22:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"e08e2f92e261bcd734231f4a131e91eb07d4df8054f1af6162dd3f2692e6a03e","abstract_canon_sha256":"4aa4085e5c434698862a2a28c69e259e5979ca11e54a373a7b1cf9e12bc9f61e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:47.081991Z","signature_b64":"gzuKy/vaB7PxwoRoVQyoy02QGwp2F8a19hTdgLIxR1LqhK4mtErMz9vh0nsn9hahxeqH7kfoifWXospujx+1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f166f67aff983355dce42083bf6b7f655bfadeff004142380ace07e01d0e366","last_reissued_at":"2026-07-14T00:18:47.080371Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:47.080371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARIMA: Reconstruction-Grounded Predictive Representation Learning for Symbolic Music","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Mingyang Yao, Zhaoxiang Feng","submitted_at":"2026-07-10T22:02:00Z","abstract_excerpt":"Self-supervised learning for symbolic music has advanced largely through token-level pretraining, but such representations remain tied to tokenizer-specific sequences and often provide time-span-level embeddings only indirectly. In this paper, we propose ARIMA, a reconstruction-grounded latent predictive framework for symbolic music that learns compact window-based representations directly from data. ARIMA encodes each fixed-duration window into a continuous latent representation, trains a causal predictor with contrastive next-latent prediction, and grounds the encoder through structured reco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10003","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/2607.10003/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":"2607.10003","created_at":"2026-07-14T00:18:47.081586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10003v1","created_at":"2026-07-14T00:18:47.081586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10003","created_at":"2026-07-14T00:18:47.081586+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4LG6Z5P7GBT","created_at":"2026-07-14T00:18:47.081586+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4LG6Z5P7GBTKXOO","created_at":"2026-07-14T00:18:47.081586+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4LG6Z5P","created_at":"2026-07-14T00:18:47.081586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04378","citing_title":"Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z","json":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z.json","graph_json":"https://pith.science/api/pith-number/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/graph.json","events_json":"https://pith.science/api/pith-number/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/events.json","paper":"https://pith.science/paper/P4LG6Z5P"},"agent_actions":{"view_html":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z","download_json":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z.json","view_paper":"https://pith.science/paper/P4LG6Z5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10003&json=true","fetch_graph":"https://pith.science/api/pith-number/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/action/storage_attestation","attest_author":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/action/author_attestation","sign_citation":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/action/citation_signature","submit_replication":"https://pith.science/pith/P4LG6Z5P7GBTKXOOIIEDX5VX6Z/action/replication_record"}},"created_at":"2026-07-14T00:18:47.081586+00:00","updated_at":"2026-07-14T00:18:47.081586+00:00"}