{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BPFFK3FGV2NGBXBKXBLF33OD2G","short_pith_number":"pith:BPFFK3FG","schema_version":"1.0","canonical_sha256":"0bca556ca6ae9a60dc2ab8565dedc3d19976f96394b5a8deb25192f26354c636","source":{"kind":"arxiv","id":"2106.00750","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Goldenberg, Danny Eytan, Sana Tonekaboni","submitted_at":"2021-06-01T19:53:24Z","abstract_excerpt":"Time series are often complex and rich in information but sparsely labeled and therefore challenging to model. In this paper, we propose a self-supervised framework for learning generalizable representations for non-stationary time series. Our approach, called Temporal Neighborhood Coding (TNC), takes advantage of the local smoothness of a signal's generative process to define neighborhoods in time with stationary properties. Using a debiased contrastive objective, our framework learns time series representations by ensuring that in the encoding space, the distribution of signals from within a"},"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":"2106.00750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T19:53:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90743e9e589b653db08dbaeb8f23d1ffb1cd296e0d63955c9d1a91cd1b798c02","abstract_canon_sha256":"32f8c34aaac8f8b578616a42f0d1cb6dd53f170c22ded15b71510991a99c40ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:39.652663Z","signature_b64":"JvWDpdqa/JnwL72L0K6Qnaqprt5MTJjGKH0TW9Nts8c4t5j+7wfZFjvu8MQId9Ap2iG4QA0bi9xXzYtiXiGQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bca556ca6ae9a60dc2ab8565dedc3d19976f96394b5a8deb25192f26354c636","last_reissued_at":"2026-07-05T02:45:39.652208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:39.652208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Goldenberg, Danny Eytan, Sana Tonekaboni","submitted_at":"2021-06-01T19:53:24Z","abstract_excerpt":"Time series are often complex and rich in information but sparsely labeled and therefore challenging to model. In this paper, we propose a self-supervised framework for learning generalizable representations for non-stationary time series. Our approach, called Temporal Neighborhood Coding (TNC), takes advantage of the local smoothness of a signal's generative process to define neighborhoods in time with stationary properties. Using a debiased contrastive objective, our framework learns time series representations by ensuring that in the encoding space, the distribution of signals from within a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00750","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/2106.00750/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":"2106.00750","created_at":"2026-07-05T02:45:39.652270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00750v1","created_at":"2026-07-05T02:45:39.652270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00750","created_at":"2026-07-05T02:45:39.652270+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPFFK3FGV2NG","created_at":"2026-07-05T02:45:39.652270+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPFFK3FGV2NGBXBK","created_at":"2026-07-05T02:45:39.652270+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPFFK3FG","created_at":"2026-07-05T02:45:39.652270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07365","citing_title":"A robust PPG foundation model using multimodal physiological supervision","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00958","citing_title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00956","citing_title":"Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16001","citing_title":"Concurrence: A dependence criterion for time series, applied to biological data","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G","json":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G.json","graph_json":"https://pith.science/api/pith-number/BPFFK3FGV2NGBXBKXBLF33OD2G/graph.json","events_json":"https://pith.science/api/pith-number/BPFFK3FGV2NGBXBKXBLF33OD2G/events.json","paper":"https://pith.science/paper/BPFFK3FG"},"agent_actions":{"view_html":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G","download_json":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G.json","view_paper":"https://pith.science/paper/BPFFK3FG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00750&json=true","fetch_graph":"https://pith.science/api/pith-number/BPFFK3FGV2NGBXBKXBLF33OD2G/graph.json","fetch_events":"https://pith.science/api/pith-number/BPFFK3FGV2NGBXBKXBLF33OD2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G/action/storage_attestation","attest_author":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G/action/author_attestation","sign_citation":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G/action/citation_signature","submit_replication":"https://pith.science/pith/BPFFK3FGV2NGBXBKXBLF33OD2G/action/replication_record"}},"created_at":"2026-07-05T02:45:39.652270+00:00","updated_at":"2026-07-05T02:45:39.652270+00:00"}