{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:67M5R3GPMMMV7JV27YI3Z7347T","short_pith_number":"pith:67M5R3GP","schema_version":"1.0","canonical_sha256":"f7d9d8eccf63195fa6bafe11bcff7cfcef7f02b1586427e656eb490c382b2ec6","source":{"kind":"arxiv","id":"2311.00519","version":4},"attestation_state":"computed","paper":{"title":"REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Moreno, Benjamin M. Marlin, Hui Wei, James M. Rehg, Maxwell A. Xu","submitted_at":"2023-11-01T13:44:45Z","abstract_excerpt":"The success of self-supervised contrastive learning hinges on identifying positive data pairs, such that when they are pushed together in embedding space, the space encodes useful information for subsequent downstream tasks. Constructing positive pairs is non-trivial as the pairing must be similar enough to reflect a shared semantic meaning, but different enough to capture within-class variation. Classical approaches in vision use augmentations to exploit well-established invariances to construct positive pairs, but invariances in the time-series domain are much less obvious. In our work, we 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":"2311.00519","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T13:44:45Z","cross_cats_sorted":[],"title_canon_sha256":"fe17fb18ee12211110ae1b90930aa3501d8d0084a9020c5931ddaaabab69a0cd","abstract_canon_sha256":"6981d16cc56a5a6c1c436f3e49ecfe56b894b258ffb86a16a4b73835220ceb44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:22.713917Z","signature_b64":"ujY03CNVHupBEKQZLKOKyaRfhm0f5/c9bvvLUVL4Mjxc03kWmevYQpMvZlmTT7IPC2V7NFQTBnyrdf8HYQ/UAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7d9d8eccf63195fa6bafe11bcff7cfcef7f02b1586427e656eb490c382b2ec6","last_reissued_at":"2026-07-05T09:26:22.712617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:22.712617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Moreno, Benjamin M. Marlin, Hui Wei, James M. Rehg, Maxwell A. Xu","submitted_at":"2023-11-01T13:44:45Z","abstract_excerpt":"The success of self-supervised contrastive learning hinges on identifying positive data pairs, such that when they are pushed together in embedding space, the space encodes useful information for subsequent downstream tasks. Constructing positive pairs is non-trivial as the pairing must be similar enough to reflect a shared semantic meaning, but different enough to capture within-class variation. Classical approaches in vision use augmentations to exploit well-established invariances to construct positive pairs, but invariances in the time-series domain are much less obvious. In our work, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00519","kind":"arxiv","version":4},"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/2311.00519/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":"2311.00519","created_at":"2026-07-05T09:26:22.712676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00519v4","created_at":"2026-07-05T09:26:22.712676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00519","created_at":"2026-07-05T09:26:22.712676+00:00"},{"alias_kind":"pith_short_12","alias_value":"67M5R3GPMMMV","created_at":"2026-07-05T09:26:22.712676+00:00"},{"alias_kind":"pith_short_16","alias_value":"67M5R3GPMMMV7JV2","created_at":"2026-07-05T09:26:22.712676+00:00"},{"alias_kind":"pith_short_8","alias_value":"67M5R3GP","created_at":"2026-07-05T09:26:22.712676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07365","citing_title":"A robust PPG foundation model using multimodal physiological supervision","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2502.16060","citing_title":"Tokenizing Single-Channel EEG with Time-Frequency Motif Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T","json":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T.json","graph_json":"https://pith.science/api/pith-number/67M5R3GPMMMV7JV27YI3Z7347T/graph.json","events_json":"https://pith.science/api/pith-number/67M5R3GPMMMV7JV27YI3Z7347T/events.json","paper":"https://pith.science/paper/67M5R3GP"},"agent_actions":{"view_html":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T","download_json":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T.json","view_paper":"https://pith.science/paper/67M5R3GP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00519&json=true","fetch_graph":"https://pith.science/api/pith-number/67M5R3GPMMMV7JV27YI3Z7347T/graph.json","fetch_events":"https://pith.science/api/pith-number/67M5R3GPMMMV7JV27YI3Z7347T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T/action/storage_attestation","attest_author":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T/action/author_attestation","sign_citation":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T/action/citation_signature","submit_replication":"https://pith.science/pith/67M5R3GPMMMV7JV27YI3Z7347T/action/replication_record"}},"created_at":"2026-07-05T09:26:22.712676+00:00","updated_at":"2026-07-05T09:26:22.712676+00:00"}