{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XHPF2IT4YWVFYRCDOKL25RDTDH","short_pith_number":"pith:XHPF2IT4","schema_version":"1.0","canonical_sha256":"b9de5d227cc5aa5c44437297aec47319e4548519acc096ac518c8dc2cdfd1ea6","source":{"kind":"arxiv","id":"2603.00190","version":2},"attestation_state":"computed","paper":{"title":"OSF: On Pre-training and Scaling of Sleep Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Yang, Wei Wang, Yuzhe Yang, Zitao Shuai, Zongzhe Xu","submitted_at":"2026-02-27T02:14:56Z","abstract_excerpt":"Polysomnography (PSG) provides the gold standard for sleep assessment but suffers from substantial heterogeneity across recording devices and cohorts. There have been growing efforts to build general-purpose foundation models (FMs) for sleep physiology, but lack an in-depth understanding of the pre-training process and scaling patterns that lead to more generalizable sleep FMs. To fill this gap, we curate a massive corpus of 166,500 hours of sleep recordings from nine public sources and establish SleepBench, a comprehensive, fully open-source benchmark. Leveraging SleepBench, we systematically"},"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":"2603.00190","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-27T02:14:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16a0a37dd048fa3551777f6009154e3c70974bfd2dc3aee25bc70570ab4c6c25","abstract_canon_sha256":"cf0b0a07df89ed776ce4a31fcd367453b63ec03ba9baf50725575e3670df0d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:35.857846Z","signature_b64":"YwNWLpZNuuMACLZ2NopG3S6maQ3mUybHZ4e1XE0YxGX7xZ6ugnGBF8hdPFgo7cu5nQK12Mw+EpmuQrG+OIy4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9de5d227cc5aa5c44437297aec47319e4548519acc096ac518c8dc2cdfd1ea6","last_reissued_at":"2026-07-07T02:18:35.856695Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:35.856695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSF: On Pre-training and Scaling of Sleep Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Yang, Wei Wang, Yuzhe Yang, Zitao Shuai, Zongzhe Xu","submitted_at":"2026-02-27T02:14:56Z","abstract_excerpt":"Polysomnography (PSG) provides the gold standard for sleep assessment but suffers from substantial heterogeneity across recording devices and cohorts. There have been growing efforts to build general-purpose foundation models (FMs) for sleep physiology, but lack an in-depth understanding of the pre-training process and scaling patterns that lead to more generalizable sleep FMs. To fill this gap, we curate a massive corpus of 166,500 hours of sleep recordings from nine public sources and establish SleepBench, a comprehensive, fully open-source benchmark. Leveraging SleepBench, we systematically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00190","kind":"arxiv","version":2},"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/2603.00190/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":"2603.00190","created_at":"2026-07-07T02:18:35.856894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.00190v2","created_at":"2026-07-07T02:18:35.856894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00190","created_at":"2026-07-07T02:18:35.856894+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHPF2IT4YWVF","created_at":"2026-07-07T02:18:35.856894+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHPF2IT4YWVFYRCD","created_at":"2026-07-07T02:18:35.856894+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHPF2IT4","created_at":"2026-07-07T02:18:35.856894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2607.06617","citing_title":"Inertia-1: An Open Exploration of Wearable Motion Foundation Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30865","citing_title":"GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09605","citing_title":"Next-Token Prediction Learns Generalisable Representations of Sleep Physiology","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21295","citing_title":"TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH","json":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH.json","graph_json":"https://pith.science/api/pith-number/XHPF2IT4YWVFYRCDOKL25RDTDH/graph.json","events_json":"https://pith.science/api/pith-number/XHPF2IT4YWVFYRCDOKL25RDTDH/events.json","paper":"https://pith.science/paper/XHPF2IT4"},"agent_actions":{"view_html":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH","download_json":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH.json","view_paper":"https://pith.science/paper/XHPF2IT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.00190&json=true","fetch_graph":"https://pith.science/api/pith-number/XHPF2IT4YWVFYRCDOKL25RDTDH/graph.json","fetch_events":"https://pith.science/api/pith-number/XHPF2IT4YWVFYRCDOKL25RDTDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH/action/storage_attestation","attest_author":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH/action/author_attestation","sign_citation":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH/action/citation_signature","submit_replication":"https://pith.science/pith/XHPF2IT4YWVFYRCDOKL25RDTDH/action/replication_record"}},"created_at":"2026-07-07T02:18:35.856894+00:00","updated_at":"2026-07-07T02:18:35.856894+00:00"}