{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LMIQODQ7PPYYOLEWFGZNK4TH3T","short_pith_number":"pith:LMIQODQ7","schema_version":"1.0","canonical_sha256":"5b11070e1f7bf1872c9629b2d57267dce845dc9579c43dee3bf2949cd1a3b719","source":{"kind":"arxiv","id":"2506.04906","version":2},"attestation_state":"computed","paper":{"title":"TRACE: Contrastive learning for multi-trial time-series data in neuroscience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Andreas Tolias, Dmitry Kobak, Dominic Gonschorek, Fabian Sinz, Jacob Reimer, Jan Niklas B\\\"ohm, Katrin Franke, Lisa Schmors, Na Zhou, Philipp Berens, Sebastian Damrich, Yongrong Qiu","submitted_at":"2025-06-05T11:40:12Z","abstract_excerpt":"Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework for learning representations of complex datasets. Existing applications for neural time series rely on generic data augmentations and do not exploit the multi-trial data structure inherent in many neural datasets. Here we present TRACE, a new contrastive learning framework that averages across different subsets of trials to generate positive pairs. TRACE allo"},"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":"2506.04906","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.NC","submitted_at":"2025-06-05T11:40:12Z","cross_cats_sorted":[],"title_canon_sha256":"c05c8668ad376913c280f930e6f1032d5b359035896c4c8327e2353f4e4d18c6","abstract_canon_sha256":"f559ed6b7df0041acb296cac8286f12c0929ba4d84e9da08643ba3cf2705817c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:06.981433Z","signature_b64":"P88ixBaV/jo5etwwfyZXDc3SWukWXPhmHLVB2cCY8yPewg0HxK2WmPjxQPirWLd3YDzJN3GVtFSfaURDuRdIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b11070e1f7bf1872c9629b2d57267dce845dc9579c43dee3bf2949cd1a3b719","last_reissued_at":"2026-06-09T01:05:06.980836Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:06.980836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRACE: Contrastive learning for multi-trial time-series data in neuroscience","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Andreas Tolias, Dmitry Kobak, Dominic Gonschorek, Fabian Sinz, Jacob Reimer, Jan Niklas B\\\"ohm, Katrin Franke, Lisa Schmors, Na Zhou, Philipp Berens, Sebastian Damrich, Yongrong Qiu","submitted_at":"2025-06-05T11:40:12Z","abstract_excerpt":"Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework for learning representations of complex datasets. Existing applications for neural time series rely on generic data augmentations and do not exploit the multi-trial data structure inherent in many neural datasets. Here we present TRACE, a new contrastive learning framework that averages across different subsets of trials to generate positive pairs. TRACE allo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04906","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/2506.04906/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":"2506.04906","created_at":"2026-06-09T01:05:06.980922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04906v2","created_at":"2026-06-09T01:05:06.980922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04906","created_at":"2026-06-09T01:05:06.980922+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMIQODQ7PPYY","created_at":"2026-06-09T01:05:06.980922+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMIQODQ7PPYYOLEW","created_at":"2026-06-09T01:05:06.980922+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMIQODQ7","created_at":"2026-06-09T01:05:06.980922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.09395","citing_title":"Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09395","citing_title":"Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08068","citing_title":"Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T","json":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T.json","graph_json":"https://pith.science/api/pith-number/LMIQODQ7PPYYOLEWFGZNK4TH3T/graph.json","events_json":"https://pith.science/api/pith-number/LMIQODQ7PPYYOLEWFGZNK4TH3T/events.json","paper":"https://pith.science/paper/LMIQODQ7"},"agent_actions":{"view_html":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T","download_json":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T.json","view_paper":"https://pith.science/paper/LMIQODQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04906&json=true","fetch_graph":"https://pith.science/api/pith-number/LMIQODQ7PPYYOLEWFGZNK4TH3T/graph.json","fetch_events":"https://pith.science/api/pith-number/LMIQODQ7PPYYOLEWFGZNK4TH3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T/action/storage_attestation","attest_author":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T/action/author_attestation","sign_citation":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T/action/citation_signature","submit_replication":"https://pith.science/pith/LMIQODQ7PPYYOLEWFGZNK4TH3T/action/replication_record"}},"created_at":"2026-06-09T01:05:06.980922+00:00","updated_at":"2026-06-09T01:05:06.980922+00:00"}