{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2JOTVY7K3UBYXFODM7YRWJD363","short_pith_number":"pith:2JOTVY7K","schema_version":"1.0","canonical_sha256":"d25d3ae3eadd038b95c367f11b247bf6c2cc522e8f5eb58f4b9cc8efe4da3611","source":{"kind":"arxiv","id":"2606.09672","version":1},"attestation_state":"computed","paper":{"title":"Correlation Is Not Enough: Embedding Human Metadata for Individual Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PF","q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Pritam Mukherjee, Saurabh Gupta, Suraj Biswas","submitted_at":"2026-06-08T15:54:28Z","abstract_excerpt":"Ask a pretrained biomedical language model whether \"cortisol 28 ug/dL\" and \"stock-market volatility\" are related, and it returns a cosine similarity of 0.83 on a scale where 1.0 means identical. The two share no mechanism. This is not a corner case: every off-the-shelf biomedical encoder we tested (BioBERT, PubMedBERT, BioM-ELECTRA) scores unrelated cross-domain pairs between 0.76 and 0.92 when the answer should be near zero. Accuracy on cross-domain discrimination is 0%.\n  Retrieval systems survive this, because a language model downstream filters the noise. A Large Behavioural Model (LBM), 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":"2606.09672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T15:54:28Z","cross_cats_sorted":["cs.CL","cs.LG","cs.PF","q-bio.QM"],"title_canon_sha256":"865ef953e17a1194a90157e58cb743ef5f33f6d0d577ae9414ecb097beb5b79c","abstract_canon_sha256":"d639c8cb69219e5e2ad3183ca42a06896c32a353f6649a8047917c31320df00a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:03.039570Z","signature_b64":"ZZ5i7tWyZA6wxgd/cvrc6l9BrcU2v1/wrcoE2uVxl4sgsLmv5FbjP9uLkXf0cD4ln6LF6KQthMCl1lfy7VjnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d25d3ae3eadd038b95c367f11b247bf6c2cc522e8f5eb58f4b9cc8efe4da3611","last_reissued_at":"2026-06-09T02:09:03.038754Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:03.038754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correlation Is Not Enough: Embedding Human Metadata for Individual Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PF","q-bio.QM"],"primary_cat":"cs.AI","authors_text":"Pritam Mukherjee, Saurabh Gupta, Suraj Biswas","submitted_at":"2026-06-08T15:54:28Z","abstract_excerpt":"Ask a pretrained biomedical language model whether \"cortisol 28 ug/dL\" and \"stock-market volatility\" are related, and it returns a cosine similarity of 0.83 on a scale where 1.0 means identical. The two share no mechanism. This is not a corner case: every off-the-shelf biomedical encoder we tested (BioBERT, PubMedBERT, BioM-ELECTRA) scores unrelated cross-domain pairs between 0.76 and 0.92 when the answer should be near zero. Accuracy on cross-domain discrimination is 0%.\n  Retrieval systems survive this, because a language model downstream filters the noise. A Large Behavioural Model (LBM), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09672","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/2606.09672/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":"2606.09672","created_at":"2026-06-09T02:09:03.038866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09672v1","created_at":"2026-06-09T02:09:03.038866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09672","created_at":"2026-06-09T02:09:03.038866+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JOTVY7K3UBY","created_at":"2026-06-09T02:09:03.038866+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JOTVY7K3UBYXFOD","created_at":"2026-06-09T02:09:03.038866+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JOTVY7K","created_at":"2026-06-09T02:09:03.038866+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/2JOTVY7K3UBYXFODM7YRWJD363","json":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363.json","graph_json":"https://pith.science/api/pith-number/2JOTVY7K3UBYXFODM7YRWJD363/graph.json","events_json":"https://pith.science/api/pith-number/2JOTVY7K3UBYXFODM7YRWJD363/events.json","paper":"https://pith.science/paper/2JOTVY7K"},"agent_actions":{"view_html":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363","download_json":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363.json","view_paper":"https://pith.science/paper/2JOTVY7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09672&json=true","fetch_graph":"https://pith.science/api/pith-number/2JOTVY7K3UBYXFODM7YRWJD363/graph.json","fetch_events":"https://pith.science/api/pith-number/2JOTVY7K3UBYXFODM7YRWJD363/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363/action/storage_attestation","attest_author":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363/action/author_attestation","sign_citation":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363/action/citation_signature","submit_replication":"https://pith.science/pith/2JOTVY7K3UBYXFODM7YRWJD363/action/replication_record"}},"created_at":"2026-06-09T02:09:03.038866+00:00","updated_at":"2026-06-09T02:09:03.038866+00:00"}