Feed API
Signals via API
Feed API access for integrations is available under Business plans. Public endpoints show a limited or redacted payload; Pro is for individual app access.
Public sample from the feed endpoint. The backend exposes read endpoints for signals, storylines, and briefings.
Public sample
GET /v1/feed/stories?limit=3&timeframe=24h&sort=momentum&tenant=biotech
{
"run_id": "4e7bc4f5-a2c6-4b84-9072-f6458f9f87ab",
"timeframe": "24h",
"items": [
{
"type": "storyline",
"id": "b06339dc-a5fa-4efa-8995-13b0cccddbec",
"story_id": "b06339dc-a5fa-4efa-8995-13b0cccddbec",
"run_id": "4e7bc4f5-a2c6-4b84-9072-f6458f9f87ab",
"snapshot_id": "ae92b679-ff72-43dd-8334-e1b4ef239420",
"narrative_id": "55bf9e9a-8038-4a6a-83e6-4c9552896209",
"first_seen": "2026-10-08T05:05:01.411215+00:00",
"last_seen": "2026-10-08T17:03:11.323683+00:00",
"first_seen_at": "2026-10-07T23:32:12.583252+00:00",
"last_seen_at": "2026-10-07T23:32:12.586795+00:00",
"status": "open",
"title": "Analytical performance of a delayed-centrifugation blood collection tube for remote blood biomarker assessment",
"summary": "Current biobanking guidelines require in-person blood collection and immediate processing for Alzheimer's disease (AD) biomarker assessment. We recently reported that the P100 blood collection tubes containing protease inhibitors improve protein biomarker stability over delayed centrifugation periods. However, whether this comparability extends beyond a small set of biomarkers to the broad panels ",
"top_tickers": [],
"why_now": [],
"metrics": {
"score_total": 0.964096,
"momentum_24h": 3,
"post_count": 3,
"unique_origin_publishers": 1,
"unique_publisher_types": 1,
"origin_share_top1": 1,
"amplifier_share_top1": null,
"duplicate_ratio": 0,
"evidence_score": 0.25,
"source_types_count": 1,
"unique_origin_domains": 1,
"unique_publishers": 1,
"quality_policy_version": 6,
"tenant_claim_coherence_policy_version": 3
},
"trend_status": "insufficient_history",
"trend_sparkline": "▁▁",
"trend_points_n": 2,
"trend_window": {
"lookback_days": 14,
"max_points": 36,
"value_key": "score_total"
},
"maturity_label": "seed",
"maturity_score": 0.25130816666666667,
"top_sources": [
{
"label": "medRxiv: Generalizing Amyloid β Pathology from Postmortem Human Brains with Vision Foundation Models for Lesion Quantification",
"source_type": "rss",
"evidence_class": "primary",
"provenance_role": "origin",
"publisher_subtype": "research"
}
],
"rank_story": 0.7862298059156128,
"p_score": 1,
"p_mom": 1,
"recency": 0.9449192236624508,
"risk_penalty": 0.1,
"badges": [
"seed",
"insufficient_history",
"low_evidence"
],
"storyline_category": "narrative",
"storyline_category_reason": "multi_run_continuity",
"verified_update_issuer_count": 1,
"storyline_independent_origin_count": 1,
"storyline_continuity_points": 2,
"sources": [],
"llm_title": "Preprints examine new approaches to Alzheimer’s pathology and biomarker measurement",
"llm_summary": "Three medRxiv preprints explore complementary Alzheimer’s disease measurement tools: region- and solubility-dependent proteomics for neurofibrillary tangle pathology, the ViTamyloid computational pathology pipeline for amyloid-beta lesion quantification, and delayed-centrifugation blood collection for high-plex biomarker assessment.",
"llm_narrative_frame": "The cluster brings together three preprint-based approaches to improving Alzheimer’s disease measurement: proteomic characterization of neurofibrillary tangle pathology across brain regions and solubility fractions, automated quantification and classification of amyloid-beta lesions in postmortem tissue, and assessment of delayed-centrifugation blood collection for high-plex biomarker testing.",
"llm_narrative_label": "Alzheimer’s measurement methods",
"llm_narrative_type": "narrative",
"llm_why_now": [
"Three fresh preprints bring related Alzheimer’s measurement methods into one research signal.",
"The cluster spans molecular profiling, computational pathology, and remote blood-biomarker assessment."
],
"llm_why_it_matters": [
"The studies address tissue characterization, pathology quantification, and blood-biomarker processing.",
"Together, they illustrate complementary efforts to make Alzheimer’s measurements more detailed or operationally consistent."
],
"llm_top_sources": [
{
"label": "Neurofibrillary tangle proteomics"
},
{
"label": "ViTamyloid pathology quantification"
},
{
"label": "Delayed-centrifugation blood biomarker assessment"
}
],
"entities": {
"projects": [
"ViTamyloid"
]
},
"recurring_claims": [
{
"claim": "The preprints target distinct measurement bottlenecks spanning tissue proteomics, computational pathology, and blood-sample handling.",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.04.26361149v1?rss=1",
"https://medrxiv.org/content/10.64898/2026.10.05.26364184v1?rss=1",
"https://medrxiv.org/content/10.64898/2026.10.05.26364780v1?rss=1"
]
},
{
"claim": "The studies examine ways to improve characterization or consistency of Alzheimer’s pathology and biomarker measurements.",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.04.26361149v1?rss=1",
"https://medrxiv.org/content/10.64898/2026.10.05.26364184v1?rss=1",
"https://medrxiv.org/content/10.64898/2026.10.05.26364780v1?rss=1"
]
}
],
"stance_map": [
{
"who": "Preprint authors",
"stance": "neutral",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.04.26361149v1?rss=1"
]
},
{
"who": "Preprint authors",
"stance": "neutral",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.05.26364184v1?rss=1"
]
},
{
"who": "Preprint authors",
"stance": "neutral",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.05.26364780v1?rss=1"
]
}
],
"quality_flags": {
"mixed_topic_risk": "low",
"promo_risk": "low",
"source_quality": "medium"
},
"editor_note": "Three medRxiv preprints address complementary measurement challenges in Alzheimer’s disease research.",
"scope_tags": [
"biotech",
"research_and_development",
"neuroscience",
"biomarkers",
"genomics",
"preprints"
],
"scope_tags_raw": [
"biotech",
"research_and_development",
"neuroscience",
"biomarkers",
"genomics",
"preprints"
],
"llm_status": "accepted",
"llm_meta": {
"model": "gpt-5.6-luna",
"prompt_version": "enrich_v3",
"input_hash": "a4edabb7b68e4f10250c2ff31ae4609ef26b3ae8ba692a106a2d028758f16e2b",
"updated_at": "2026-10-08T17:05:40.719477+00:00",
"llm_metadata": {
"env": "prod",
"host": "83bc069ed062",
"stage": "signals.enrich",
"run_id": "4e7bc4f5-a2c6-4b84-9072-f6458f9f87ab",
"tenant": "biotech",
"service": "api",
"pipeline": "pipeline_run",
"correlation_id": "55bf9e9a-8038-4a6a-83e6-4c9552896209"
}
},
"display_title": "Preprints examine new approaches to Alzheimer’s pathology and biomarker measurement",
"display_summary": "Three medRxiv preprints explore complementary Alzheimer’s disease measurement tools: region- and solubility-dependent proteomics for neurofibrillary tangle pathology, the ViTamyloid computational pathology pipeline for amyloid-beta lesion quantification, and...",
"display_tags": [
"biotech",
"research_and_development",
"neuroscience",
"biomarkers",
"genomics",
"preprints"
],
"tags": [
"biotech",
"research_and_development",
"neuroscience",
"biomarkers",
"genomics",
"preprints"
],
"cscope_tags": [
"biotech",
"research_and_development",
"neuroscience",
"biomarkers",
"genomics",
"preprints"
],
"display_why_now": [
"Three fresh preprints bring related Alzheimer’s measurement methods into one research signal.",
"The cluster spans molecular profiling, computational pathology, and remote blood-biomarker assessment."
],
"display_why_it_matters": [
"The studies address tissue characterization, pathology quantification, and blood-biomarker processing.",
"Together, they illustrate complementary efforts to make Alzheimer’s measurements more detailed or operationally consistent."
],
"why_now_display": [
"Three fresh preprints bring related Alzheimer’s measurement methods into one research signal.",
"The cluster spans molecular profiling, computational pathology, and remote blood-biomarker assessment."
],
"why_it_matters_display": [
"The studies address tissue characterization, pathology quantification, and blood-biomarker processing.",
"Together, they illustrate complementary efforts to make Alzheimer’s measurements more detailed or operationally consistent."
],
"show_why": true,
"sources_display": [
{
"label": "medrxiv.org: ViTamyloid pathology quantification"
}
],
"editor_status": "passed",
"fields_replaced": [],
"narrative_frame_display": "The cluster brings together three preprint-based approaches to improving Alzheimer’s disease measurement: proteomic characterization of neurofibrillary tangle pathology across brain regions and solubility fractions, automated quantification and classification of amyloid-beta lesions in postmortem tissue, and assessment of delayed-centrifugation blood collection for high-plex biomarker testing.",
"display_rank_base_score": 3,
"display_rank_score": 1000000003,
"display_rank_boost": 1000000000,
"lane": "chatter",
"lane_reason": "maturity=seed",
"evidence_mix": {
"primary": 1,
"secondary": 0,
"specialist": 0,
"aggregator": 0,
"social": 0
},
"sourceStats": {
"qualityPolicyVersion": 6,
"evidenceDocumentCount": 3,
"uniqueItemCount": 3,
"uniquePublisherCount": 1,
"uniqueCanonicalOriginCount": 1,
"independentNonSocialCount": 1,
"primaryCount": 1,
"secondaryCount": 0,
"uniqueDomainsCount": 1,
"aggregatorCount": 0,
"socialCount": 0,
"sourceTypeDiversityCount": 1,
"topSourceShare": 1,
"passesTopSignalsGate": false,
"gateReason": "independentNonSocial=1; primary=1; secondary=0; documents=3; publishers=1; canonicalOrigins=1; topSourceShare=1.0; rule=>=2 unique canonical primary/secondary publishers; aggregators/social excluded"
},
"evidence_meta": {
"post_count": 3,
"unique_origin_publishers": 1,
"source_types_count": 1,
"origin_share_top1": 1
},
"gate": {
"passesTopSignalsGate": false,
"gateReason": "independentNonSocial=1; primary=1; secondary=0; documents=3; publishers=1; canonicalOrigins=1; topSourceShare=1.0; rule=>=2 unique canonical primary/secondary publishers; aggregators/social excluded"
},
"tenant_claim_coherence": {
"tenant": "biotech",
"status": "not_applicable",
"claim_scope": "not_applicable",
"reason_codes": [],
"public_anchors": {},
"evidence_anchors": {},
"debug": {
"evidence_record_count": 3,
"matching_record_count": 0,
"independent_support_count": 0,
"conflicting_record_count": 0
}
},
"evidence_quality_flag": "weak"
},
{
"type": "storyline",
"id": "7ef3e500-fc38-4b11-9e77-e0077b1f99ef",
"story_id": "7ef3e500-fc38-4b11-9e77-e0077b1f99ef",
"run_id": "4e7bc4f5-a2c6-4b84-9072-f6458f9f87ab",
"snapshot_id": "b566c61e-4d8d-4acd-be7d-e1c99a587cd1",
"narrative_id": "7d236e53-1b53-40df-8cdc-6de92c191731",
"first_seen": "2026-10-08T05:05:01.411215+00:00",
"last_seen": "2026-10-08T17:03:11.323683+00:00",
"first_seen_at": "2026-10-07T23:32:12.586936+00:00",
"last_seen_at": "2026-10-08T00:12:01.194822+00:00",
"status": "open",
"title": "Forecasting Alzheimer's disease progression using non-imaging clinical features and XGBoost",
"summary": "Identifying progressive dementia during its prodromal stage is a challenging yet critical task for healthcare providers. Traditional clinical assessments are often not sensitive enough to detect warning signs of cognitive decline. Machine learning (ML) methods have shown promise in modeling clinical trajectories associated with neurodegenerative disorders such as Alzheimer's disease (AD). Validati",
"top_tickers": [],
"why_now": [],
"metrics": {
"score_total": 0.718271,
"momentum_24h": 2,
"post_count": 2,
"unique_origin_publishers": 1,
"unique_publisher_types": 1,
"origin_share_top1": 1,
"amplifier_share_top1": null,
"duplicate_ratio": 0,
"evidence_score": 0.25,
"source_types_count": 1,
"unique_origin_domains": 1,
"unique_publishers": 1,
"quality_policy_version": 6,
"tenant_claim_coherence_policy_version": 3
},
"trend_status": "insufficient_history",
"trend_sparkline": "▁▁",
"trend_points_n": 2,
"trend_window": {
"lookback_days": 14,
"max_points": 36,
"value_key": "score_total"
},
"maturity_label": "seed",
"maturity_score": 0.24870716666666667,
"top_sources": [
{
"label": "medRxiv: Use of routine clinical data in adults with chronic diseases for identifying risk of frailty: results from the UK Biobank study",
"source_type": "rss",
"evidence_class": "primary",
"provenance_role": "origin",
"publisher_subtype": "research"
}
],
"rank_story": 0.0362298059156127,
"p_score": 0,
"p_mom": 0,
"recency": 0.9449192236624508,
"risk_penalty": 0.1,
"badges": [
"seed",
"insufficient_history",
"low_evidence"
],
"storyline_category": "narrative",
"storyline_category_reason": "multi_run_continuity",
"verified_update_issuer_count": 1,
"storyline_independent_origin_count": 1,
"storyline_continuity_points": 2,
"sources": [],
"llm_title": "Preprints test clinical data models for frailty and Alzheimer's risk prediction",
"llm_summary": "Two medRxiv preprints assess machine-learning approaches to clinical risk prediction. One uses routine measures to prioritize frailty screening in adults with chronic diseases; the other uses longitudinal, non-imaging clinical data and XGBoost to forecast progression from normal cognition to mild cognitive impairment and from mild cognitive impairment to Alzheimer's disease.",
"llm_narrative_frame": "The cluster highlights two preprints using routinely collected, non-imaging clinical data to support earlier risk identification: one prioritizes frailty assessment in adults with chronic diseases, while the other forecasts transitions from normal cognition to mild cognitive impairment and from mild cognitive impairment to Alzheimer's disease.",
"llm_narrative_label": "Clinical data models for risk prediction",
"llm_narrative_type": "ongoing_storyline",
"llm_why_now": [
"Two related preprints appeared within the same monitoring window.",
"The studies apply machine learning to large longitudinal or population datasets.",
"The findings are preprints and do not establish clinical implementation."
],
"llm_why_it_matters": [
"Routine clinical measures could help prioritize resource-intensive frailty assessments.",
"Non-imaging models offer a studied approach to forecasting cognitive decline.",
"Both preprints focus on earlier identification using existing clinical data."
],
"llm_top_sources": [
{
"label": "Routine clinical data for frailty risk"
},
{
"label": "Non-imaging forecasting of Alzheimer's progression"
}
],
"entities": {
"projects": [
"UK Biobank",
"National Alzheimer's Coordinating Center"
]
},
"recurring_claims": [
{
"claim": "A UK Biobank study evaluates a stacked ensemble using 12 routine, low-cost clinical variables to prioritize frailty assessment among adults with chronic diseases.",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.05.26364730v1?rss=1"
]
},
{
"claim": "A longitudinal National Alzheimer's Coordinating Center study uses non-imaging clinical features and XGBoost to forecast cognitive-status transitions.",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.05.26364229v1?rss=1"
]
}
],
"stance_map": [
{
"who": "Landre et al.",
"stance": "neutral",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.05.26364730v1?rss=1"
]
},
{
"who": "Gautier et al.",
"stance": "neutral",
"evidence_urls": [
"https://medrxiv.org/content/10.64898/2026.10.05.26364229v1?rss=1"
]
}
],
"quality_flags": {
"mixed_topic_risk": "low",
"promo_risk": "low",
"source_quality": "medium"
},
"editor_note": "Two medRxiv preprints examine machine-learning models for earlier clinical risk identification; both remain early-stage research.",
"scope_tags": [
"clinical_research",
"machine_learning",
"risk_stratification",
"frailty",
"alzheimers_disease",
"preprints"
],
"scope_tags_raw": [
"clinical_research",
"machine_learning",
"risk_stratification",
"frailty",
"alzheimers_disease",
"preprints"
],
"llm_status": "accepted",
"llm_meta": {
"model": "gpt-5.6-luna",
"prompt_version": "enrich_v3",
"input_hash": "ea66032b2cb69f46a67e996da7f05546cf97b983e10a5d8054d0524b7ad39573",
"updated_at": "2026-10-08T17:05:40.839436+00:00",
"llm_metadata": {
"env": "prod",
"host": "83bc069ed062",
"stage": "signals.enrich",
"run_id": "4e7bc4f5-a2c6-4b84-9072-f6458f9f87ab",
"tenant": "biotech",
"service": "api",
"pipeline": "pipeline_run",
"correlation_id": "7d236e53-1b53-40df-8cdc-6de92c191731"
}
},
"display_title": "Preprints test clinical data models for frailty and Alzheimer's risk prediction",
"display_summary": "Two medRxiv preprints assess machine-learning approaches to clinical risk prediction.",
"display_tags": [
"clinical_research",
"machine_learning",
"risk_stratification",
"frailty",
"alzheimers_disease",
"preprints"
],
"tags": [
"clinical_research",
"machine_learning",
"risk_stratification",
"frailty",
"alzheimers_disease",
"preprints"
],
"cscope_tags": [
"clinical_research",
"machine_learning",
"risk_stratification",
"frailty",
"alzheimers_disease",
"preprints"
],
"display_why_now": [
"Two related preprints appeared within the same monitoring window.",
"The studies apply machine learning to large longitudinal or population datasets.",
"The findings are preprints and do not establish clinical implementation."
],
"display_why_it_matters": [
"Routine clinical measures could help prioritize resource-intensive frailty assessments.",
"Non-imaging models offer a studied approach to forecasting cognitive decline.",
"Both preprints focus on earlier identification using existing clinical data."
],
"why_now_display": [
"Two related preprints appeared within the same monitoring window.",
"The studies apply machine learning to large longitudinal or population datasets.",
"The findings are preprints and do not establish clinical implementation."
],
"why_it_matters_display": [
"Routine clinical measures could help prioritize resource-intensive frailty assessments.",
"Non-imaging models offer a studied approach to forecasting cognitive decline.",
"Both preprints focus on earlier identification using existing clinical data."
],
"show_why": true,
"sources_display": [
{
"label": "medrxiv.org: Routine clinical data for frailty risk"
}
],
"editor_status": "passed",
"fields_replaced": [],
"narrative_frame_display": "The cluster highlights two preprints using routinely collected, non-imaging clinical data to support earlier risk identification: one prioritizes frailty assessment in adults with chronic diseases, while the other forecasts transitions from normal cognition to mild cognitive impairment and from mild cognitive impairment to Alzheimer's disease.",
"display_rank_base_score": 2,
"display_rank_score": 1000000002,
"display_rank_boost": 1000000000,
"lane": "chatter",
"lane_reason": "maturity=seed",
"evidence_mix": {
"primary": 1,
"secondary": 0,
"specialist": 0,
"aggregator": 0,
"social": 0
},
"sourceStats": {
"qualityPolicyVersion": 6,
"evidenceDocumentCount": 2,
"uniqueItemCount": 2,
"uniquePublisherCount": 1,
"uniqueCanonicalOriginCount": 1,
"independentNonSocialCount": 1,
"primaryCount": 1,
"secondaryCount": 0,
"uniqueDomainsCount": 1,
"aggregatorCount": 0,
"socialCount": 0,
"sourceTypeDiversityCount": 1,
"topSourceShare": 1,
"passesTopSignalsGate": false,
"gateReason": "independentNonSocial=1; primary=1; secondary=0; documents=2; publishers=1; canonicalOrigins=1; topSourceShare=1.0; rule=>=2 unique canonical primary/secondary publishers; aggregators/social excluded"
},
"evidence_meta": {
"post_count": 2,
"unique_origin_publishers": 1,
"source_types_count": 1,
"origin_share_top1": 1
},
"gate": {
"passesTopSignalsGate": false,
"gateReason": "independentNonSocial=1; primary=1; secondary=0; documents=2; publishers=1; canonicalOrigins=1; topSourceShare=1.0; rule=>=2 unique canonical primary/secondary publishers; aggregators/social excluded"
},
"tenant_claim_coherence": {
"tenant": "biotech",
"status": "not_applicable",
"claim_scope": "not_applicable",
"reason_codes": [],
"public_anchors": {},
"evidence_anchors": {
"product": [
"biobank"
]
},
"debug": {
"evidence_record_count": 2,
"matching_record_count": 0,
"independent_support_count": 0,
"conflicting_record_count": 0
}
},
"evidence_quality_flag": "weak"
}
],
"next_cursor": null,
"disclaimer": "No investment advice. Research signals and sources only. EarlyNarratives provides informational signals derived from public sources. It does not provide financial, legal, or tax advice."
}Capabilities
- Signals and storylines feed endpoints with filtering and rate limits
- Briefing delivery endpoints for integrations
- Evidence link payloads for auditability
Integrate in your workflow
- Route top stories into Slack or Teams for morning and evening desk updates.
- Sync storyline evidence into Notion, Airtable, or internal research trackers.
- Feed metrics into BI dashboards for momentum, concentration, and source mix monitoring.
Quick start endpoints: /v1/feed/stories, /v1/signals, /v1/storylines/search, /v1/briefings/latest.
For product access, see Pricing.