{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SF22N6DWQSR4YBLDHFLBZS652B","short_pith_number":"pith:SF22N6DW","schema_version":"1.0","canonical_sha256":"9175a6f87684a3cc056339561ccbddd05780bc1fe5b89afd04083bebd4db97ee","source":{"kind":"arxiv","id":"2607.03356","version":1},"attestation_state":"computed","paper":{"title":"CaReCoS: A Spectrogram based Visual Benchmark for Cardiac, Respiratory and Cough Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abhishek Mukherji, Akhil Pothanapalli, Asif Shaik, Harshit Rajgarhia, Prasanna Desikan, Rachuri Lokesh, Shuubham Ojha","submitted_at":"2026-07-03T14:14:04Z","abstract_excerpt":"Medical acoustic signals such as respiratory sounds, cardiac auscultations, and cough audio carry rich diagnostic information, yet no existing benchmark evaluates multimodal reasoning over their spectrogram representations. We address both gaps with CaReCoS, a benchmark pairing clinically grounded questions with mel-spectrogram images derived from seven medical audio datasets. Evaluating 9 state-of-the-art vision and omni models, we find that all struggle with fine-grained acoustic features encoded in spectrograms: no model reliably combines visual pattern recognition with medical knowledge, 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":"2607.03356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-03T14:14:04Z","cross_cats_sorted":[],"title_canon_sha256":"0f5db23f3043d11a396c828b60b3c870053e50e4ef72e091821501e8c7b98623","abstract_canon_sha256":"bf1bf25e72689203a9fc65ed9bca56aff76f372588e9ad952c331b1302c2aedd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:38.899804Z","signature_b64":"8dgRZqIQJMDA82E06fI96V1G0nOrYErazgR76hOG7fuU0XyC9JDwQFyPh/FVjhRd5CQtmwCUkEslGQNu4231CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9175a6f87684a3cc056339561ccbddd05780bc1fe5b89afd04083bebd4db97ee","last_reissued_at":"2026-07-07T02:17:38.896279Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:38.896279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaReCoS: A Spectrogram based Visual Benchmark for Cardiac, Respiratory and Cough Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abhishek Mukherji, Akhil Pothanapalli, Asif Shaik, Harshit Rajgarhia, Prasanna Desikan, Rachuri Lokesh, Shuubham Ojha","submitted_at":"2026-07-03T14:14:04Z","abstract_excerpt":"Medical acoustic signals such as respiratory sounds, cardiac auscultations, and cough audio carry rich diagnostic information, yet no existing benchmark evaluates multimodal reasoning over their spectrogram representations. We address both gaps with CaReCoS, a benchmark pairing clinically grounded questions with mel-spectrogram images derived from seven medical audio datasets. Evaluating 9 state-of-the-art vision and omni models, we find that all struggle with fine-grained acoustic features encoded in spectrograms: no model reliably combines visual pattern recognition with medical knowledge, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03356","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/2607.03356/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":"2607.03356","created_at":"2026-07-07T02:17:38.898625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03356v1","created_at":"2026-07-07T02:17:38.898625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03356","created_at":"2026-07-07T02:17:38.898625+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF22N6DWQSR4","created_at":"2026-07-07T02:17:38.898625+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF22N6DWQSR4YBLD","created_at":"2026-07-07T02:17:38.898625+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF22N6DW","created_at":"2026-07-07T02:17:38.898625+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/SF22N6DWQSR4YBLDHFLBZS652B","json":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B.json","graph_json":"https://pith.science/api/pith-number/SF22N6DWQSR4YBLDHFLBZS652B/graph.json","events_json":"https://pith.science/api/pith-number/SF22N6DWQSR4YBLDHFLBZS652B/events.json","paper":"https://pith.science/paper/SF22N6DW"},"agent_actions":{"view_html":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B","download_json":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B.json","view_paper":"https://pith.science/paper/SF22N6DW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03356&json=true","fetch_graph":"https://pith.science/api/pith-number/SF22N6DWQSR4YBLDHFLBZS652B/graph.json","fetch_events":"https://pith.science/api/pith-number/SF22N6DWQSR4YBLDHFLBZS652B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B/action/storage_attestation","attest_author":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B/action/author_attestation","sign_citation":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B/action/citation_signature","submit_replication":"https://pith.science/pith/SF22N6DWQSR4YBLDHFLBZS652B/action/replication_record"}},"created_at":"2026-07-07T02:17:38.898625+00:00","updated_at":"2026-07-07T02:17:38.898625+00:00"}