{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:K46YEPRKSCNPGZQQFZNZL2EFUX","short_pith_number":"pith:K46YEPRK","schema_version":"1.0","canonical_sha256":"573d823e2a909af366102e5b95e885a5fd2f1ab0ca7ad5cb87db1b968ded3724","source":{"kind":"arxiv","id":"1907.05321","version":1},"attestation_state":"computed","paper":{"title":"Time2Vec: Learning a Vector Representation of Time","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cathal Smyth, Janahan Ramanan, Jaspreet Sahota, Marcus Brubaker, Pascal Poupart, Rishab Goel, Sanjay Thakur, Sepehr Eghbali, Seyed Mehran Kazemi, Stella Wu","submitted_at":"2019-07-11T15:47:39Z","abstract_excerpt":"Time is an important feature in many applications involving events that occur synchronously and/or asynchronously. To effectively consume time information, recent studies have focused on designing new architectures. In this paper, we take an orthogonal but complementary approach by providing a model-agnostic vector representation for time, called Time2Vec, that can be easily imported into many existing and future architectures and improve their performances. We show on a range of models and problems that replacing the notion of time with its Time2Vec representation improves the performance of "},"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":"1907.05321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T15:47:39Z","cross_cats_sorted":[],"title_canon_sha256":"5a3929ee6f3555219ec0677026aec1342ecef8e38bf45b3cf65d3ccd52a65cb5","abstract_canon_sha256":"9a78d11f32084fbf2c4f2c8d57696d56d67e5c32def353963bbb09f2651187ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:50.746068Z","signature_b64":"ktV+wSP1XftIUF39uKSfLsHyBGZIUusnXAcYIrvOlZ7XzeXl4u2PsVlOseWSLDYbRwUXFWTUz4VVfwTgFkeYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"573d823e2a909af366102e5b95e885a5fd2f1ab0ca7ad5cb87db1b968ded3724","last_reissued_at":"2026-05-17T23:40:50.745377Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:50.745377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time2Vec: Learning a Vector Representation of Time","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cathal Smyth, Janahan Ramanan, Jaspreet Sahota, Marcus Brubaker, Pascal Poupart, Rishab Goel, Sanjay Thakur, Sepehr Eghbali, Seyed Mehran Kazemi, Stella Wu","submitted_at":"2019-07-11T15:47:39Z","abstract_excerpt":"Time is an important feature in many applications involving events that occur synchronously and/or asynchronously. To effectively consume time information, recent studies have focused on designing new architectures. In this paper, we take an orthogonal but complementary approach by providing a model-agnostic vector representation for time, called Time2Vec, that can be easily imported into many existing and future architectures and improve their performances. We show on a range of models and problems that replacing the notion of time with its Time2Vec representation improves the performance of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05321","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":""},"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":"1907.05321","created_at":"2026-05-17T23:40:50.745484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05321v1","created_at":"2026-05-17T23:40:50.745484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05321","created_at":"2026-05-17T23:40:50.745484+00:00"},{"alias_kind":"pith_short_12","alias_value":"K46YEPRKSCNP","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"K46YEPRKSCNPGZQQ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"K46YEPRK","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.16208","citing_title":"A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2006.10637","citing_title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2602.00520","citing_title":"NEST: Nested Event Stream Transformer for Sequences of Multisets","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2602.10385","citing_title":"Capture Timing-Attention of Events in Clinical Time Series","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06227","citing_title":"A Benchmark of Classical and Deep Learning Models for Agricultural Commodity Price Forecasting on A Novel Bangladeshi Market Price Dataset","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13711","citing_title":"MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12335","citing_title":"EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01134","citing_title":"To Use AI as Dice of Possibilities with Timing Computation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22077","citing_title":"Empirical Assessment of Time-Series Foundation Models For Power System Forecasting Applications","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21623","citing_title":"A-THENA: Early Intrusion Detection for IoT with Time-Aware Hybrid Encoding and Network-Specific Augmentation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11842","citing_title":"DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06906","citing_title":"TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06990","citing_title":"TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06726","citing_title":"Transformer-Based Wildlife Species Classification from Daily Movement Trajectories","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16775","citing_title":"Representation Before Training: A Fixed-Budget Benchmark for Generative Medical Event Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17419","citing_title":"ARMove: Learning to Predict Human Mobility through Agentic Reasoning","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX","json":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX.json","graph_json":"https://pith.science/api/pith-number/K46YEPRKSCNPGZQQFZNZL2EFUX/graph.json","events_json":"https://pith.science/api/pith-number/K46YEPRKSCNPGZQQFZNZL2EFUX/events.json","paper":"https://pith.science/paper/K46YEPRK"},"agent_actions":{"view_html":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX","download_json":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX.json","view_paper":"https://pith.science/paper/K46YEPRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05321&json=true","fetch_graph":"https://pith.science/api/pith-number/K46YEPRKSCNPGZQQFZNZL2EFUX/graph.json","fetch_events":"https://pith.science/api/pith-number/K46YEPRKSCNPGZQQFZNZL2EFUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX/action/storage_attestation","attest_author":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX/action/author_attestation","sign_citation":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX/action/citation_signature","submit_replication":"https://pith.science/pith/K46YEPRKSCNPGZQQFZNZL2EFUX/action/replication_record"}},"created_at":"2026-05-17T23:40:50.745484+00:00","updated_at":"2026-05-17T23:40:50.745484+00:00"}