{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5T3S2U5JXOAOQOA7GHZ4B7DGAX","short_pith_number":"pith:5T3S2U5J","schema_version":"1.0","canonical_sha256":"ecf72d53a9bb80e8381f31f3c0fc6605c6e526a35fc504af4e0c2b7f53913e44","source":{"kind":"arxiv","id":"2412.14373","version":3},"attestation_state":"computed","paper":{"title":"ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.CL","authors_text":"Chaojing Duan, Ding Zhao, Emerson Liu, Michael A. Rosenberg, William Han","submitted_at":"2024-12-18T22:13:21Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional versatility across domains, including applications to electrocardiograms (ECGs). A growing body of work focuses on generating text from multi-channeled ECG signals and corresponding textual prompts. Existing approaches often involve a two-stage process: pretraining an ECG-specific encoder with a self-supervised learning (SSL) objective, followed by finetuning an LLM for natural language generation (NLG) using encoder-derived features. However, these methods face two key limitations: inefficiency due to multi-stage training and challeng"},"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":"2412.14373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T22:13:21Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"17083395ba4a7341e8bfd1604e9c6d0009b45fa2bd0c3692be07f6607dc36b05","abstract_canon_sha256":"818839d9c43bb87598a7d2688a4dd40aa0dbd494c68b13531166657e5c62aeae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:13.912476Z","signature_b64":"tdA5DH/ACg0fyer5utTh+BQ6LabQfE+58USDbMkYZctfEeEzamdNPy/h0+mqSX5rnLxT3WuOk+WhvHWIpMA6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf72d53a9bb80e8381f31f3c0fc6605c6e526a35fc504af4e0c2b7f53913e44","last_reissued_at":"2026-07-05T11:45:13.912015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:13.912015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.CL","authors_text":"Chaojing Duan, Ding Zhao, Emerson Liu, Michael A. Rosenberg, William Han","submitted_at":"2024-12-18T22:13:21Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional versatility across domains, including applications to electrocardiograms (ECGs). A growing body of work focuses on generating text from multi-channeled ECG signals and corresponding textual prompts. Existing approaches often involve a two-stage process: pretraining an ECG-specific encoder with a self-supervised learning (SSL) objective, followed by finetuning an LLM for natural language generation (NLG) using encoder-derived features. However, these methods face two key limitations: inefficiency due to multi-stage training and challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14373","kind":"arxiv","version":3},"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/2412.14373/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":"2412.14373","created_at":"2026-07-05T11:45:13.912073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14373v3","created_at":"2026-07-05T11:45:13.912073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14373","created_at":"2026-07-05T11:45:13.912073+00:00"},{"alias_kind":"pith_short_12","alias_value":"5T3S2U5JXOAO","created_at":"2026-07-05T11:45:13.912073+00:00"},{"alias_kind":"pith_short_16","alias_value":"5T3S2U5JXOAOQOA7","created_at":"2026-07-05T11:45:13.912073+00:00"},{"alias_kind":"pith_short_8","alias_value":"5T3S2U5J","created_at":"2026-07-05T11:45:13.912073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27583","citing_title":"Information-theoretic Multimodal Representation Learning for Electrocardiogram Signals","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX","json":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX.json","graph_json":"https://pith.science/api/pith-number/5T3S2U5JXOAOQOA7GHZ4B7DGAX/graph.json","events_json":"https://pith.science/api/pith-number/5T3S2U5JXOAOQOA7GHZ4B7DGAX/events.json","paper":"https://pith.science/paper/5T3S2U5J"},"agent_actions":{"view_html":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX","download_json":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX.json","view_paper":"https://pith.science/paper/5T3S2U5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14373&json=true","fetch_graph":"https://pith.science/api/pith-number/5T3S2U5JXOAOQOA7GHZ4B7DGAX/graph.json","fetch_events":"https://pith.science/api/pith-number/5T3S2U5JXOAOQOA7GHZ4B7DGAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX/action/storage_attestation","attest_author":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX/action/author_attestation","sign_citation":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX/action/citation_signature","submit_replication":"https://pith.science/pith/5T3S2U5JXOAOQOA7GHZ4B7DGAX/action/replication_record"}},"created_at":"2026-07-05T11:45:13.912073+00:00","updated_at":"2026-07-05T11:45:13.912073+00:00"}