{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IIT7QJGPKSXS76MOLSVRA2DQRB","short_pith_number":"pith:IIT7QJGP","canonical_record":{"source":{"id":"2604.14615","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T04:47:55Z","cross_cats_sorted":[],"title_canon_sha256":"ccba6313644bedd099c3e6ffc030a5bb85fe6acaa41b9211c65d2c7663754ea3","abstract_canon_sha256":"780c99402f9ebad50dd0274b51f7241b4c4198f4b6e9943459db77b1ff90b7e6"},"schema_version":"1.0"},"canonical_sha256":"4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89","source":{"kind":"arxiv","id":"2604.14615","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.14615","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2604.14615v2","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14615","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"IIT7QJGPKSXS","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"IIT7QJGPKSXS76MO","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"IIT7QJGP","created_at":"2026-06-23T01:12:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IIT7QJGPKSXS76MOLSVRA2DQRB","target":"record","payload":{"canonical_record":{"source":{"id":"2604.14615","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T04:47:55Z","cross_cats_sorted":[],"title_canon_sha256":"ccba6313644bedd099c3e6ffc030a5bb85fe6acaa41b9211c65d2c7663754ea3","abstract_canon_sha256":"780c99402f9ebad50dd0274b51f7241b4c4198f4b6e9943459db77b1ff90b7e6"},"schema_version":"1.0"},"canonical_sha256":"4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:07.184889Z","signature_b64":"BSkA/7vz+MHQVWN4YQwmRHkS6e6zF3XlgsRRG9lcwbhxSDHLq0VDmjrmNcZBssc5GFc3+N9KBGe8K3f/4C/1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89","last_reissued_at":"2026-06-23T01:12:07.184388Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:07.184388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.14615","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eleBhK3Va1Ca66d9d6i6mh4yVzeD/+a32PF2VabwCYrAz+5I9lsn5qg/tstsfHoejGs3PZ12JPa5jzjhq9xqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:47:35.213168Z"},"content_sha256":"e28e9a66c8788628d4736313353f4eb9727062eea1c9991dec4a7b300d193f8e","schema_version":"1.0","event_id":"sha256:e28e9a66c8788628d4736313353f4eb9727062eea1c9991dec4a7b300d193f8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IIT7QJGPKSXS76MOLSVRA2DQRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"A. Ali Heydari, Ahmed A. Metwally, Alan Karthikesalingam, Annalisa Pawlosky, Chunjong Park, Cynthia Breazeal, Daniel McDuff, Dongjae Lee, Elahe Vedadi, Hae Won Park, Hamid Palangi, Hanseul Cho, Hong Yu, Hyeonhoon Lee, Hyewon Jeong, Ivor Rendulic, Juraj Gottweis, Kyungho Lim, Mark Malhotra, Maxwell A. Xu, Mingyu Lu, Nicolas Stroppa, Petar Sirkovic, Pushmeet Kohli, Salman Rahman, Samir Tulebaev, Samuel Schmidgall, Shwetak Patel, Theodora Pappa, Tim Althoff, Vivek Natarajan, Xin Liu, Xuhai Xu, Yubin Kim, Yuzhe Yang, Zhihan Zhang","submitted_at":"2026-04-16T04:47:55Z","abstract_excerpt":"Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across three cohorts totaling 9,279 participant-observations, CoDaS identified 41 candidate digital biomarkers for mental health and 25 for metabolic outcomes... Incorporating CoDaS-derived features alongside demographic variables led to modest but consistent improvements in predictive performance, with cross-validated ΔR² increases of 0.040 for depression and 0.021 for insulin resistance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The multi-agent AI system with adversarial validation and human oversight can generate and prioritize hypotheses that are both novel and clinically meaningful without introducing systematic bias or over-fitting to the specific datasets used.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CoDaS, a multi-agent AI co-data-scientist, identifies 41 mental health and 25 metabolic digital biomarkers from 9,279 wearable observations, replicates some circadian features across cohorts, and yields modest predictive gains when added to demographic models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"87efff5097696979198e008d751d70f72eccc37e4ffbc5a85d1e383af28ce39a"},"source":{"id":"2604.14615","kind":"arxiv","version":2},"verdict":{"id":"5f5dcf3a-967c-43f6-b641-f946a63b5053","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T10:58:17.263194Z","strongest_claim":"Across three cohorts totaling 9,279 participant-observations, CoDaS identified 41 candidate digital biomarkers for mental health and 25 for metabolic outcomes... Incorporating CoDaS-derived features alongside demographic variables led to modest but consistent improvements in predictive performance, with cross-validated ΔR² increases of 0.040 for depression and 0.021 for insulin resistance.","one_line_summary":"CoDaS, a multi-agent AI co-data-scientist, identifies 41 mental health and 25 metabolic digital biomarkers from 9,279 wearable observations, replicates some circadian features across cohorts, and yields modest predictive gains when added to demographic models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The multi-agent AI system with adversarial validation and human oversight can generate and prioritize hypotheses that are both novel and clinically meaningful without introducing systematic bias or over-fitting to the specific datasets used.","pith_extraction_headline":"A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.14615/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"},"verdict_id":"5f5dcf3a-967c-43f6-b641-f946a63b5053"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0uA1+Q22isSVv2H7GUStOzfXz3fhKR3uc26dS/TUUmbvwtw/ovddHAcPiUm3iuNFGCDuZZsan4jjfUMGjGgaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:47:35.213897Z"},"content_sha256":"4c5c5c3a5c294267b175f55758add36baae216a3ac86346836bbf5539a06e20e","schema_version":"1.0","event_id":"sha256:4c5c5c3a5c294267b175f55758add36baae216a3ac86346836bbf5539a06e20e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIT7QJGPKSXS76MOLSVRA2DQRB/bundle.json","state_url":"https://pith.science/pith/IIT7QJGPKSXS76MOLSVRA2DQRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIT7QJGPKSXS76MOLSVRA2DQRB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T19:47:35Z","links":{"resolver":"https://pith.science/pith/IIT7QJGPKSXS76MOLSVRA2DQRB","bundle":"https://pith.science/pith/IIT7QJGPKSXS76MOLSVRA2DQRB/bundle.json","state":"https://pith.science/pith/IIT7QJGPKSXS76MOLSVRA2DQRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIT7QJGPKSXS76MOLSVRA2DQRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IIT7QJGPKSXS76MOLSVRA2DQRB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"780c99402f9ebad50dd0274b51f7241b4c4198f4b6e9943459db77b1ff90b7e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T04:47:55Z","title_canon_sha256":"ccba6313644bedd099c3e6ffc030a5bb85fe6acaa41b9211c65d2c7663754ea3"},"schema_version":"1.0","source":{"id":"2604.14615","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.14615","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2604.14615v2","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14615","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"IIT7QJGPKSXS","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"IIT7QJGPKSXS76MO","created_at":"2026-06-23T01:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"IIT7QJGP","created_at":"2026-06-23T01:12:07Z"}],"graph_snapshots":[{"event_id":"sha256:4c5c5c3a5c294267b175f55758add36baae216a3ac86346836bbf5539a06e20e","target":"graph","created_at":"2026-06-23T01:12:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across three cohorts totaling 9,279 participant-observations, CoDaS identified 41 candidate digital biomarkers for mental health and 25 for metabolic outcomes... Incorporating CoDaS-derived features alongside demographic variables led to modest but consistent improvements in predictive performance, with cross-validated ΔR² increases of 0.040 for depression and 0.021 for insulin resistance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The multi-agent AI system with adversarial validation and human oversight can generate and prioritize hypotheses that are both novel and clinically meaningful without introducing systematic bias or over-fitting to the specific datasets used."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CoDaS, a multi-agent AI co-data-scientist, identifies 41 mental health and 25 metabolic digital biomarkers from 9,279 wearable observations, replicates some circadian features across cohorts, and yields modest predictive gains when added to demographic models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts."}],"snapshot_sha256":"87efff5097696979198e008d751d70f72eccc37e4ffbc5a85d1e383af28ce39a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.14615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robu","authors_text":"A. Ali Heydari, Ahmed A. Metwally, Alan Karthikesalingam, Annalisa Pawlosky, Chunjong Park, Cynthia Breazeal, Daniel McDuff, Dongjae Lee, Elahe Vedadi, Hae Won Park, Hamid Palangi, Hanseul Cho, Hong Yu, Hyeonhoon Lee, Hyewon Jeong, Ivor Rendulic, Juraj Gottweis, Kyungho Lim, Mark Malhotra, Maxwell A. Xu, Mingyu Lu, Nicolas Stroppa, Petar Sirkovic, Pushmeet Kohli, Salman Rahman, Samir Tulebaev, Samuel Schmidgall, Shwetak Patel, Theodora Pappa, Tim Althoff, Vivek Natarajan, Xin Liu, Xuhai Xu, Yubin Kim, Yuzhe Yang, Zhihan Zhang","cross_cats":[],"headline":"A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T04:47:55Z","title":"An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.14615","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T10:58:17.263194Z","id":"5f5dcf3a-967c-43f6-b641-f946a63b5053","model_set":{"reader":"grok-4.3"},"one_line_summary":"CoDaS, a multi-agent AI co-data-scientist, identifies 41 mental health and 25 metabolic digital biomarkers from 9,279 wearable observations, replicates some circadian features across cohorts, and yields modest predictive gains when added to demographic models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A multi-agent AI system discovers 66 candidate digital biomarkers from wearable sensor data across large cohorts.","strongest_claim":"Across three cohorts totaling 9,279 participant-observations, CoDaS identified 41 candidate digital biomarkers for mental health and 25 for metabolic outcomes... Incorporating CoDaS-derived features alongside demographic variables led to modest but consistent improvements in predictive performance, with cross-validated ΔR² increases of 0.040 for depression and 0.021 for insulin resistance.","weakest_assumption":"The multi-agent AI system with adversarial validation and human oversight can generate and prioritize hypotheses that are both novel and clinically meaningful without introducing systematic bias or over-fitting to the specific datasets used."}},"verdict_id":"5f5dcf3a-967c-43f6-b641-f946a63b5053"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e28e9a66c8788628d4736313353f4eb9727062eea1c9991dec4a7b300d193f8e","target":"record","created_at":"2026-06-23T01:12:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"780c99402f9ebad50dd0274b51f7241b4c4198f4b6e9943459db77b1ff90b7e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T04:47:55Z","title_canon_sha256":"ccba6313644bedd099c3e6ffc030a5bb85fe6acaa41b9211c65d2c7663754ea3"},"schema_version":"1.0","source":{"id":"2604.14615","kind":"arxiv","version":2}},"canonical_sha256":"4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4227f824cf54af2ff98e5cab1068708841ecc5f723d6438c75db80a4dd16da89","first_computed_at":"2026-06-23T01:12:07.184388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:07.184388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BSkA/7vz+MHQVWN4YQwmRHkS6e6zF3XlgsRRG9lcwbhxSDHLq0VDmjrmNcZBssc5GFc3+N9KBGe8K3f/4C/1Dg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:07.184889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.14615","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e28e9a66c8788628d4736313353f4eb9727062eea1c9991dec4a7b300d193f8e","sha256:4c5c5c3a5c294267b175f55758add36baae216a3ac86346836bbf5539a06e20e"],"state_sha256":"b4d5c01df7ad1e95209183ab4a41a5cfa8af7a33667e85ae1fc81dd5d1b7ea21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Cj8VuXTfeuT8qL8lAM3yYWTuchBh9vkFo5IC3ZEDc+0IX+e9TyGb0PzKzzEtXio2GUu1hTshmL/gtC2ACBlBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T19:47:35.219495Z","bundle_sha256":"b0ffd008216f847dbed04af999c658a10e16961f9578558638a8b453e14e1008"}}