{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3XSV7YHWKR55ZXY2ZTDURL5BHA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f3e08e5f4569d21ca0d8d2515a15cba0ddb8d160b12ca20d02017617b34ed80c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T18:27:25Z","title_canon_sha256":"18237cea6659be67281c31f121860757aaee10310756657ab02fdb7dd5b16642"},"schema_version":"1.0","source":{"id":"2605.14014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14014","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14014v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14014","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"3XSV7YHWKR55","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"3XSV7YHWKR55ZXY2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"3XSV7YHW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:631bb49586c98ff0bf63ba32736f59c5efcd5ca22e48fdcd37d824931eb9c886","target":"graph","created_at":"2026-05-17T23:39:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive evaluations on five real-world IoT sensing datasets across activity recognition, stress assessment, and nearby object detection demonstrate that Dywave outperforms state-of-the-art methods by up to 12% in accuracy, while improving computational efficiency by reducing input token lengths by up to 75% across mainstream sequence models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That wavelet-based hierarchical decomposition can reliably and automatically identify meaningful temporal boundaries that correspond to underlying semantic events in heterogeneous, non-stationary IoT signals without task-specific tuning that would limit generality."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Dywave applies wavelet-based hierarchical decomposition to build dynamic, event-aligned tokens for heterogeneous IoT signals, cutting token length by up to 75% while raising accuracy up to 12% on sequence models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Dywave uses wavelet decomposition to align tokens with semantic events in IoT signals."}],"snapshot_sha256":"e51196e8075d83610538b6f875e14dbfbb068381015d5c379f5c44844949e330"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"54265c59cb8236fde0fa94a20a90681bf69eca529632618715cd157911cd97b7"},"paper":{"abstract_excerpt":"Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous sensors to support intelligent applications such as human activity analysis, emotion monitoring, and environmental perception. These signals are inherently non-stationary and multi-scale, posing unique challenges for standard tokenization techniques. This paper proposes Dywave, a dynamic tokenization framework for IoT sensing signals that constructs compact input representations aligned with intrinsic temporal structures and underlying physical events. Dywave leverages wavelet-based hierarchical","authors_text":"Denizhan Kara, Hongjue Zhao, Jinyang Li, Shengzhong Liu, Tarek Abdelzaher, Tomoyoshi Kimura, Xiaomin Ouyang, Yigong Hu, Yizhuo Chen","cross_cats":["cs.AI"],"headline":"Dywave uses wavelet decomposition to align tokens with semantic events in IoT signals.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T18:27:25Z","title":"Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signal"},"references":{"count":300,"internal_anchors":3,"resolved_work":300,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Ahia, O., Kumar, S., Gonen, H., Kasai, J., Mortensen, D. R., Smith, N. A., and Tsvetkov, Y. Do all languages cost the same? tokenization in the era of commercial language models","work_id":"69d9a5a0-a56f-4495-b183-b5f2589cc2f0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"K., and Alshurafa, N","work_id":"2364a9db-c101-4aa2-a9f1-3075925fc100","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"F., Stella, L., Turkmen, A","work_id":"860815ec-6f22-4f9f-a419-011a8b0c27a4","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Foundation models for cps-iot: Opportunities and challenges","work_id":"f4b3f8a1-4cf1-4387-8fdc-6274882f9da6","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M","work_id":"40fb82bf-2dd3-47b9-b780-b8a213cdfe2b","year":2021}],"snapshot_sha256":"8aa01116dedf2580c6b9cb2f47ef9bd8cb199352aaf0aed41eb152a3a3494f0a"},"source":{"id":"2605.14014","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:40:27.518834Z","id":"e0817ee4-b739-467e-8682-4c1a02980e6f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Dywave applies wavelet-based hierarchical decomposition to build dynamic, event-aligned tokens for heterogeneous IoT signals, cutting token length by up to 75% while raising accuracy up to 12% on sequence models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Dywave uses wavelet decomposition to align tokens with semantic events in IoT signals.","strongest_claim":"Extensive evaluations on five real-world IoT sensing datasets across activity recognition, stress assessment, and nearby object detection demonstrate that Dywave outperforms state-of-the-art methods by up to 12% in accuracy, while improving computational efficiency by reducing input token lengths by up to 75% across mainstream sequence models.","weakest_assumption":"That wavelet-based hierarchical decomposition can reliably and automatically identify meaningful temporal boundaries that correspond to underlying semantic events in heterogeneous, non-stationary IoT signals without task-specific tuning that would limit generality."}},"verdict_id":"e0817ee4-b739-467e-8682-4c1a02980e6f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95a5774ee47db0cf02e5dc0fa14dcd38c277c1fb6ee30d424b28fd973928f001","target":"record","created_at":"2026-05-17T23:39:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f3e08e5f4569d21ca0d8d2515a15cba0ddb8d160b12ca20d02017617b34ed80c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T18:27:25Z","title_canon_sha256":"18237cea6659be67281c31f121860757aaee10310756657ab02fdb7dd5b16642"},"schema_version":"1.0","source":{"id":"2605.14014","kind":"arxiv","version":1}},"canonical_sha256":"dde55fe0f6547bdcdf1accc748afa13809eaac077c744fb30aef71006fcee99e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dde55fe0f6547bdcdf1accc748afa13809eaac077c744fb30aef71006fcee99e","first_computed_at":"2026-05-17T23:39:13.030844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:13.030844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pj88TGJ8JcLSALelCfuzFEiCJ2E5JwpdGfD4rWMuRBV6uAoFNQZVGPgyRGogm96Xrjpf5EJtJD8rqH9UY5RvBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:13.031500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95a5774ee47db0cf02e5dc0fa14dcd38c277c1fb6ee30d424b28fd973928f001","sha256:631bb49586c98ff0bf63ba32736f59c5efcd5ca22e48fdcd37d824931eb9c886"],"state_sha256":"a80a3b44ba48c16124c915341e3a6d379093f73b53ef8659f38830aa05727e51"}