{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BGHEEHJASENPYOMFSTPNI2DRYV","short_pith_number":"pith:BGHEEHJA","schema_version":"1.0","canonical_sha256":"098e421d20911afc398594ded46871c55d5f5558e0651f9786c464ba0100cfb6","source":{"kind":"arxiv","id":"2604.09450","version":2},"attestation_state":"computed","paper":{"title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A one-step block diffusion model generates clinically accurate chest X-ray reports eight times faster than autoregressive methods by distilling joint token dependencies.","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.LG","authors_text":"Hao Liu, Jile Jiao, Lifeng Chen, Tao Sun, Tianqi You, Xiaofeng Mou, Xiao Han, Xiaojie Jin, Yi Xu, Zhicai Ou, Zhimin Bao","submitted_at":"2026-04-10T16:07:14Z","abstract_excerpt":"Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive vision--language models (VLMs) suffer from high inference latency due to sequential token decoding. Diffusion-based models offer a promising alternative through parallel generation, but they still require multiple denoising iterations. Compressing multi-step denoising to a single step could further reduce latency, but often degrades textual coherence due to the mean-field bias introduced by token-factorized denoisers. To address this challenge, we pro"},"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":"2604.09450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-10T16:07:14Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"b2af0b2c94d7ddaf1f807a8ba8fba25bf1d35880301fe0a175e7c792bb2b7b7d","abstract_canon_sha256":"689ae9778f9f72a1df5c06ff46733e928ce5dc0c1d874f7c4852dca7abcfb449"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:31.209792Z","signature_b64":"QbC0k/t5a3YbWbeYHJl4hmcO3IjYD/sT23g2S4AJAH4Ii4sEibYMGC669I1E2QUbqDAdn+Z/g7x+M/PKADXuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"098e421d20911afc398594ded46871c55d5f5558e0651f9786c464ba0100cfb6","last_reissued_at":"2026-05-20T00:04:31.208955Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:31.208955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A one-step block diffusion model generates clinically accurate chest X-ray reports eight times faster than autoregressive methods by distilling joint token dependencies.","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.LG","authors_text":"Hao Liu, Jile Jiao, Lifeng Chen, Tao Sun, Tianqi You, Xiaofeng Mou, Xiao Han, Xiaojie Jin, Yi Xu, Zhicai Ou, Zhimin Bao","submitted_at":"2026-04-10T16:07:14Z","abstract_excerpt":"Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive vision--language models (VLMs) suffer from high inference latency due to sequential token decoding. Diffusion-based models offer a promising alternative through parallel generation, but they still require multiple denoising iterations. Compressing multi-step denoising to a single step could further reduce latency, but often degrades textual coherence due to the mean-field bias introduced by token-factorized denoisers. To address this challenge, we pro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ECHO surpasses state-of-the-art autoregressive methods, improving RaTE and SemScore by 64.33% and 60.58% respectively, while achieving an 8× inference speedup without compromising clinical accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Direct Conditional Distillation framework successfully encodes joint token dependencies from on-policy trajectories to overcome mean-field bias in one-step generation, without introducing new coherence failures not captured by the reported metrics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ECHO is a one-step block diffusion VLM for chest X-ray reports that improves RaTE and SemScore by over 60% while delivering 8x faster inference than autoregressive baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A one-step block diffusion model generates clinically accurate chest X-ray reports eight times faster than autoregressive methods by distilling joint token dependencies.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0368b12deb3cc1fc660fbc314a48e5d2b13dc69a39d0d86cf4b7a821adaa67f1"},"source":{"id":"2604.09450","kind":"arxiv","version":2},"verdict":{"id":"c0edf919-dd39-4141-94bf-9f28d67de499","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:51:46.575571Z","strongest_claim":"ECHO surpasses state-of-the-art autoregressive methods, improving RaTE and SemScore by 64.33% and 60.58% respectively, while achieving an 8× inference speedup without compromising clinical accuracy.","one_line_summary":"ECHO is a one-step block diffusion VLM for chest X-ray reports that improves RaTE and SemScore by over 60% while delivering 8x faster inference than autoregressive baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Direct Conditional Distillation framework successfully encodes joint token dependencies from on-policy trajectories to overcome mean-field bias in one-step generation, without introducing new coherence failures not captured by the reported metrics.","pith_extraction_headline":"A one-step block diffusion model generates clinically accurate chest X-ray reports eight times faster than autoregressive methods by distilling joint token dependencies."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09450/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":"2604.09450","created_at":"2026-05-20T00:04:31.209095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09450v2","created_at":"2026-05-20T00:04:31.209095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09450","created_at":"2026-05-20T00:04:31.209095+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGHEEHJASENP","created_at":"2026-05-20T00:04:31.209095+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGHEEHJASENPYOMF","created_at":"2026-05-20T00:04:31.209095+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGHEEHJA","created_at":"2026-05-20T00:04:31.209095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17071","citing_title":"AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV","json":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV.json","graph_json":"https://pith.science/api/pith-number/BGHEEHJASENPYOMFSTPNI2DRYV/graph.json","events_json":"https://pith.science/api/pith-number/BGHEEHJASENPYOMFSTPNI2DRYV/events.json","paper":"https://pith.science/paper/BGHEEHJA"},"agent_actions":{"view_html":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV","download_json":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV.json","view_paper":"https://pith.science/paper/BGHEEHJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09450&json=true","fetch_graph":"https://pith.science/api/pith-number/BGHEEHJASENPYOMFSTPNI2DRYV/graph.json","fetch_events":"https://pith.science/api/pith-number/BGHEEHJASENPYOMFSTPNI2DRYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV/action/storage_attestation","attest_author":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV/action/author_attestation","sign_citation":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV/action/citation_signature","submit_replication":"https://pith.science/pith/BGHEEHJASENPYOMFSTPNI2DRYV/action/replication_record"}},"created_at":"2026-05-20T00:04:31.209095+00:00","updated_at":"2026-05-20T00:04:31.209095+00:00"}