{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IIZ5GNYZ4QKEBETSP25AMOBKJX","short_pith_number":"pith:IIZ5GNYZ","canonical_record":{"source":{"id":"2506.00134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T18:11:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"319f02f6804603df8fd30a64910497db6fc38f3490e6fd04845c0bec53b406ad","abstract_canon_sha256":"d36693c8d6ac86d51ca4716c1197791bbc0bbb56bf28679b956f94cec7b716c0"},"schema_version":"1.0"},"canonical_sha256":"4233d33719e4144092727eba06382a4df54ce692556d723e9c6532f46e4f5ab7","source":{"kind":"arxiv","id":"2506.00134","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00134","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00134v1","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00134","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"IIZ5GNYZ4QKE","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"IIZ5GNYZ4QKEBETS","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"IIZ5GNYZ","created_at":"2026-07-05T11:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IIZ5GNYZ4QKEBETSP25AMOBKJX","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T18:11:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"319f02f6804603df8fd30a64910497db6fc38f3490e6fd04845c0bec53b406ad","abstract_canon_sha256":"d36693c8d6ac86d51ca4716c1197791bbc0bbb56bf28679b956f94cec7b716c0"},"schema_version":"1.0"},"canonical_sha256":"4233d33719e4144092727eba06382a4df54ce692556d723e9c6532f46e4f5ab7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:29.500525Z","signature_b64":"BeTnzU8P3MFbAGtfXg6M2TBLDYKq0+crS2KhxB6EQ/fJ+Cm47xvQMdik6LVVStExBgXcYgNALXXIkigmKQ4pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4233d33719e4144092727eba06382a4df54ce692556d723e9c6532f46e4f5ab7","last_reissued_at":"2026-07-05T11:13:29.500091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:29.500091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00134","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Tg5HcRYs/wr4vgee0cDqqcxzzjRBwdDFMDYUHyofmdl41d0pLdJAkeHSHqRo1T8udm+ARrxHwEaFfhqZ/F2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:03:16.790042Z"},"content_sha256":"c761e6aa39e328de13aba6d1d0e0eae14c5a5f43273e33037471f613a21706e7","schema_version":"1.0","event_id":"sha256:c761e6aa39e328de13aba6d1d0e0eae14c5a5f43273e33037471f613a21706e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IIZ5GNYZ4QKEBETSP25AMOBKJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fardin Ahsan Sakib, Karen Trister Grace, Meliha Yetisgen, Ozlem Uzuner, Ziwei Zhu","submitted_at":"2025-05-30T18:11:33Z","abstract_excerpt":"Social determinants of health (SDOH) extraction from clinical text is critical for downstream healthcare analytics. Although large language models (LLMs) have shown promise, they may rely on superficial cues leading to spurious predictions. Using the MIMIC portion of the SHAC (Social History Annotation Corpus) dataset and focusing on drug status extraction as a case study, we demonstrate that mentions of alcohol or smoking can falsely induce models to predict current/past drug use where none is present, while also uncovering concerning gender disparities in model performance. We further evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00134","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/2506.00134/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gDtS8nUIKjzcGeSf69d28MRKqVXuxmqVRFVZolxQy/C8aY7QbRxGSVpS4AJILxpBMgoHIpfB45jSXOZO4xlgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:03:16.790551Z"},"content_sha256":"d056278f27643fe5812b4ac5d716adc785706750be4811e65fa8bbd8a8e884a7","schema_version":"1.0","event_id":"sha256:d056278f27643fe5812b4ac5d716adc785706750be4811e65fa8bbd8a8e884a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX/bundle.json","state_url":"https://pith.science/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX/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":"2026-08-08T18:03:16Z","links":{"resolver":"https://pith.science/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX","bundle":"https://pith.science/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX/bundle.json","state":"https://pith.science/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIZ5GNYZ4QKEBETSP25AMOBKJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IIZ5GNYZ4QKEBETSP25AMOBKJX","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":"d36693c8d6ac86d51ca4716c1197791bbc0bbb56bf28679b956f94cec7b716c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T18:11:33Z","title_canon_sha256":"319f02f6804603df8fd30a64910497db6fc38f3490e6fd04845c0bec53b406ad"},"schema_version":"1.0","source":{"id":"2506.00134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00134","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00134v1","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00134","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"IIZ5GNYZ4QKE","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"IIZ5GNYZ4QKEBETS","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"IIZ5GNYZ","created_at":"2026-07-05T11:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:d056278f27643fe5812b4ac5d716adc785706750be4811e65fa8bbd8a8e884a7","target":"graph","created_at":"2026-07-05T11:13:29Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.00134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social determinants of health (SDOH) extraction from clinical text is critical for downstream healthcare analytics. Although large language models (LLMs) have shown promise, they may rely on superficial cues leading to spurious predictions. Using the MIMIC portion of the SHAC (Social History Annotation Corpus) dataset and focusing on drug status extraction as a case study, we demonstrate that mentions of alcohol or smoking can falsely induce models to predict current/past drug use where none is present, while also uncovering concerning gender disparities in model performance. We further evalua","authors_text":"Fardin Ahsan Sakib, Karen Trister Grace, Meliha Yetisgen, Ozlem Uzuner, Ziwei Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T18:11:33Z","title":"Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00134","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c761e6aa39e328de13aba6d1d0e0eae14c5a5f43273e33037471f613a21706e7","target":"record","created_at":"2026-07-05T11:13:29Z","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":"d36693c8d6ac86d51ca4716c1197791bbc0bbb56bf28679b956f94cec7b716c0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T18:11:33Z","title_canon_sha256":"319f02f6804603df8fd30a64910497db6fc38f3490e6fd04845c0bec53b406ad"},"schema_version":"1.0","source":{"id":"2506.00134","kind":"arxiv","version":1}},"canonical_sha256":"4233d33719e4144092727eba06382a4df54ce692556d723e9c6532f46e4f5ab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4233d33719e4144092727eba06382a4df54ce692556d723e9c6532f46e4f5ab7","first_computed_at":"2026-07-05T11:13:29.500091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:29.500091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BeTnzU8P3MFbAGtfXg6M2TBLDYKq0+crS2KhxB6EQ/fJ+Cm47xvQMdik6LVVStExBgXcYgNALXXIkigmKQ4pDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:29.500525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c761e6aa39e328de13aba6d1d0e0eae14c5a5f43273e33037471f613a21706e7","sha256:d056278f27643fe5812b4ac5d716adc785706750be4811e65fa8bbd8a8e884a7"],"state_sha256":"6804c1bd8ccab40fc3d76707637ee7e62d78210f7cb35c39b744f2ce34d53227"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYW8r74WjAsxrcyMn2xhElU+tnLcInrF6k99TCvPNjY4XZJbHwDYGuC4JDtB0kQoeYCUI8LUMhKTeakH2qutCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:03:16.794158Z","bundle_sha256":"0d5c06835c1b40c9948848cfd0df58e3af887f5d10b3d1e1353d0f3da88de388"}}