{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XGLKOTVMNGMSFILFVUVY57WZ2Y","short_pith_number":"pith:XGLKOTVM","schema_version":"1.0","canonical_sha256":"b996a74eac699922a165ad2b8efed9d61f1d40ebc70e5a8671eb0c8ef48c9200","source":{"kind":"arxiv","id":"2505.18847","version":1},"attestation_state":"computed","paper":{"title":"Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Atharva Mhaskar, Chaojing Duan, Ding Zhao, Dylan Leong, Emerson Liu, Michael A. Rosenberg, William Han, Xiaoyu Song, Yihang Yao, Zhepeng Cen","submitted_at":"2025-05-24T19:43:15Z","abstract_excerpt":"Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Conditioned on an ECG and a textual query, an ELM autoregressively generates a free-form textual response. Unlike traditional classification-based systems, ELMs emulate expert cardiac electrophysiologists by issuing diagnoses, analyzing waveform morphology, identifying contributing factors, and proposing patient-specific action plans. To realize this potential, researchers are curating instruction-tuning datasets that pair EC"},"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":"2505.18847","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-24T19:43:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"967df33d6fc72d66dc2fa4226c4666fd7b51baf0f89bee780fd28f21f237499d","abstract_canon_sha256":"c4805dc70de8a97040209fe77858cf96d50cc54eab1bff04e31da85196167d37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:20.529194Z","signature_b64":"Usqg1ZfAn6NQ7t9QK29wJcWT5a3U0137UKl5vBHho17hM69cDFXGbuyk5hsLZMqhpUFXP9jlPXQ54HWG9TtlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b996a74eac699922a165ad2b8efed9d61f1d40ebc70e5a8671eb0c8ef48c9200","last_reissued_at":"2026-07-05T11:09:20.528716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:20.528716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Atharva Mhaskar, Chaojing Duan, Ding Zhao, Dylan Leong, Emerson Liu, Michael A. Rosenberg, William Han, Xiaoyu Song, Yihang Yao, Zhepeng Cen","submitted_at":"2025-05-24T19:43:15Z","abstract_excerpt":"Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Conditioned on an ECG and a textual query, an ELM autoregressively generates a free-form textual response. Unlike traditional classification-based systems, ELMs emulate expert cardiac electrophysiologists by issuing diagnoses, analyzing waveform morphology, identifying contributing factors, and proposing patient-specific action plans. To realize this potential, researchers are curating instruction-tuning datasets that pair EC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18847","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/2505.18847/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":"2505.18847","created_at":"2026-07-05T11:09:20.528774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18847v1","created_at":"2026-07-05T11:09:20.528774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18847","created_at":"2026-07-05T11:09:20.528774+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGLKOTVMNGMS","created_at":"2026-07-05T11:09:20.528774+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGLKOTVMNGMSFILF","created_at":"2026-07-05T11:09:20.528774+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGLKOTVM","created_at":"2026-07-05T11:09:20.528774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y","json":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y.json","graph_json":"https://pith.science/api/pith-number/XGLKOTVMNGMSFILFVUVY57WZ2Y/graph.json","events_json":"https://pith.science/api/pith-number/XGLKOTVMNGMSFILFVUVY57WZ2Y/events.json","paper":"https://pith.science/paper/XGLKOTVM"},"agent_actions":{"view_html":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y","download_json":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y.json","view_paper":"https://pith.science/paper/XGLKOTVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18847&json=true","fetch_graph":"https://pith.science/api/pith-number/XGLKOTVMNGMSFILFVUVY57WZ2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/XGLKOTVMNGMSFILFVUVY57WZ2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y/action/storage_attestation","attest_author":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y/action/author_attestation","sign_citation":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y/action/citation_signature","submit_replication":"https://pith.science/pith/XGLKOTVMNGMSFILFVUVY57WZ2Y/action/replication_record"}},"created_at":"2026-07-05T11:09:20.528774+00:00","updated_at":"2026-07-05T11:09:20.528774+00:00"}