{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2Q2PKTMXT2SWZEH2KVBBIJ6B7O","short_pith_number":"pith:2Q2PKTMX","schema_version":"1.0","canonical_sha256":"d434f54d979ea56c90fa55421427c1fbbe5428f9663d911344ea32d9a25fc578","source":{"kind":"arxiv","id":"2508.10147","version":1},"attestation_state":"computed","paper":{"title":"rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mahsa Shoaran, Pascal Frossard, William Cappelletti, Yuhan Xie","submitted_at":"2025-08-13T19:16:47Z","abstract_excerpt":"Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for classification -- often outperform their counterparts trained from scratch. Still, the choice of pretext training tasks is often heuristic and their transferability to downstream classification is not granted, thus we propose a novel semi-supervised pre-training strategy to enforce latent representations that satisfy the Neural Collapse phenomenon observed i"},"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":"2508.10147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T19:16:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"642bdbb733dfb42ee2df7149500b3880217df0bf0f105fa213b61fdf3f93f569","abstract_canon_sha256":"c2307d0988f88ff3725b0fb49cfe9b6178c911e4aebe0984914660f31109dce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:32.575282Z","signature_b64":"YtNC+8IKG/aUuMpa/ljQi5quS3fNyNs9R+rSljgWLApNBZTBoKx9bKveGboDFF4pGCcnJn5RLbggs3wmQsUXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d434f54d979ea56c90fa55421427c1fbbe5428f9663d911344ea32d9a25fc578","last_reissued_at":"2026-07-05T11:53:32.574797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:32.574797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mahsa Shoaran, Pascal Frossard, William Cappelletti, Yuhan Xie","submitted_at":"2025-08-13T19:16:47Z","abstract_excerpt":"Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising results in pre-training large models, which -- when finetuned for classification -- often outperform their counterparts trained from scratch. Still, the choice of pretext training tasks is often heuristic and their transferability to downstream classification is not granted, thus we propose a novel semi-supervised pre-training strategy to enforce latent representations that satisfy the Neural Collapse phenomenon observed i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10147","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/2508.10147/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":"2508.10147","created_at":"2026-07-05T11:53:32.574854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10147v1","created_at":"2026-07-05T11:53:32.574854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10147","created_at":"2026-07-05T11:53:32.574854+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q2PKTMXT2SW","created_at":"2026-07-05T11:53:32.574854+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q2PKTMXT2SWZEH2","created_at":"2026-07-05T11:53:32.574854+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q2PKTMX","created_at":"2026-07-05T11:53:32.574854+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/2Q2PKTMXT2SWZEH2KVBBIJ6B7O","json":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O.json","graph_json":"https://pith.science/api/pith-number/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/graph.json","events_json":"https://pith.science/api/pith-number/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/events.json","paper":"https://pith.science/paper/2Q2PKTMX"},"agent_actions":{"view_html":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O","download_json":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O.json","view_paper":"https://pith.science/paper/2Q2PKTMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10147&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/action/storage_attestation","attest_author":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/action/author_attestation","sign_citation":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/action/citation_signature","submit_replication":"https://pith.science/pith/2Q2PKTMXT2SWZEH2KVBBIJ6B7O/action/replication_record"}},"created_at":"2026-07-05T11:53:32.574854+00:00","updated_at":"2026-07-05T11:53:32.574854+00:00"}