{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7UP6QXXSIDKM6TSFYOBVX7UR6Y","short_pith_number":"pith:7UP6QXXS","canonical_record":{"source":{"id":"2605.14380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T05:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"0ba45982fd8aac4c1c3e1d34462bfefd6a58015016f379a12bf04e6084df709c","abstract_canon_sha256":"0bfde37e9a47731c4290b5beeae63d3b0dbe33432c017850c17b81040de4b13b"},"schema_version":"1.0"},"canonical_sha256":"fd1fe85ef240d4cf4e45c3835bfe91f600e63492dde99b315ec404b1c86643a4","source":{"kind":"arxiv","id":"2605.14380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14380","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14380v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14380","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"7UP6QXXSIDKM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7UP6QXXSIDKM6TSF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7UP6QXXS","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7UP6QXXSIDKM6TSFYOBVX7UR6Y","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T05:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"0ba45982fd8aac4c1c3e1d34462bfefd6a58015016f379a12bf04e6084df709c","abstract_canon_sha256":"0bfde37e9a47731c4290b5beeae63d3b0dbe33432c017850c17b81040de4b13b"},"schema_version":"1.0"},"canonical_sha256":"fd1fe85ef240d4cf4e45c3835bfe91f600e63492dde99b315ec404b1c86643a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.735337Z","signature_b64":"bMjPJ9D6hSRb0Gdil7gl7I1OXx3ljiU87mtZa2W6NvUiXvXsCbZA6GOxUh1hMYwy038y/wy/sM3ygKadM+JxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1fe85ef240d4cf4e45c3835bfe91f600e63492dde99b315ec404b1c86643a4","last_reissued_at":"2026-05-17T23:39:07.734629Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.734629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14380","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":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMjByZAEg+FHmbEANaMXU5fKip7meljAWFshEYI2EfB831TJtCXegfiDE3k9o+XEy2gF699gpphiAEjPlTjVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:09:05.413490Z"},"content_sha256":"c18aacbb87840c230ee33b7d8d9e741f3f28d1cecab7a2d3d1db9c39c93123c1","schema_version":"1.0","event_id":"sha256:c18aacbb87840c230ee33b7d8d9e741f3f28d1cecab7a2d3d1db9c39c93123c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7UP6QXXSIDKM6TSFYOBVX7UR6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Context-aware synthetic augmentation with hybrid modeling lifts psychological defense mechanism classification to 58.26% accuracy under data scarcity.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hoang-Thuy-Duong Vu, Huy-Hieu Pham, Quoc-Cuong Pham","submitted_at":"2026-05-14T05:02:34Z","abstract_excerpt":"Psychological defense mechanisms (PDMs) are unconscious cognitive processes that modulate how individuals perceive and respond to emotional distress. Automatically classifying PDMs from text is clinically valuable but severely hindered by data scarcity and class imbalance, challenges which generative augmentation alone cannot resolve without psychological grounding. In this work, we address these challenges in the PsyDefDetect shared task (BioNLP@ACL 2026) by proposing a context-aware synthetic augmentation framework combined with a hybrid classification model. Our hybrid model integrates cont"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our method surpasses DMRS Co-Pilot, reaching an accuracy of 58.26% (+40.25%) and a macro-F1 of 24.62% (+15.99%), thereby establishing a strong baseline for psychologically grounded defense mechanism classification in low-resource settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That synthetic examples generated by prompting with defense-mechanism definitions maintain sufficient psychological fidelity to improve downstream classification without introducing artifacts or label noise.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A context-aware synthetic augmentation framework with a hybrid clinical-language model improves psychological defense mechanism classification to 58.26% accuracy and 24.62% macro-F1 in low-resource conditions, outperforming the DMRS Co-Pilot baseline.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Context-aware synthetic augmentation with hybrid modeling lifts psychological defense mechanism classification to 58.26% accuracy under data scarcity.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"283e7a063c9ffd2d29752dee4694636243aae8f26fae933c86a6e08e65071284"},"source":{"id":"2605.14380","kind":"arxiv","version":1},"verdict":{"id":"7bd0a031-8a1c-4d25-8a5c-ffadf9fe41f5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:31:21.429442Z","strongest_claim":"Our method surpasses DMRS Co-Pilot, reaching an accuracy of 58.26% (+40.25%) and a macro-F1 of 24.62% (+15.99%), thereby establishing a strong baseline for psychologically grounded defense mechanism classification in low-resource settings.","one_line_summary":"A context-aware synthetic augmentation framework with a hybrid clinical-language model improves psychological defense mechanism classification to 58.26% accuracy and 24.62% macro-F1 in low-resource conditions, outperforming the DMRS Co-Pilot baseline.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That synthetic examples generated by prompting with defense-mechanism definitions maintain sufficient psychological fidelity to improve downstream classification without introducing artifacts or label noise.","pith_extraction_headline":"Context-aware synthetic augmentation with hybrid modeling lifts psychological defense mechanism classification to 58.26% accuracy under data scarcity."},"references":{"count":40,"sample":[{"doi":"","year":2024,"title":"2024 , url =","work_id":"d51311f2-60b6-40bd-accd-d57ff34092cf","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Focal Loss for Dense Object Detection , year=","work_id":"a0889e1e-a3c0-4f1c-bf9c-ee77d24e2418","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3209978.3210080","year":2018,"title":"Texygen: A benchmarking platform for text generation models","work_id":"0423f1a3-61f7-42b2-96e9-4a7e00c4dcb0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Supervised Multimodal Bitransformers for Classifying Images and Text , author=. 2020 , eprint=","work_id":"2c3d1df6-bd43-4a91-97f6-73bf25e5e5c3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Educational and Psychological Measurement , year=","work_id":"79c59a9e-5727-4129-8764-d56d6f236ed4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":40,"snapshot_sha256":"d171be1211b9329c6272a1039d70b00492c0db98b02ac68d5b073148e4796904","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":"7bd0a031-8a1c-4d25-8a5c-ffadf9fe41f5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9YQ0nTHDCC5+K05Nd+firt0nbzmS6+cxGB1Ch6PgM4inHuXY/Uy7u6DG+AtCNJL8HEsN68md6pW0/ZGaHtI+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:09:05.414599Z"},"content_sha256":"5dd7b4db1e2a08c705923e52e21ea2937458c487d6f964c7dbcdbe07684f4faf","schema_version":"1.0","event_id":"sha256:5dd7b4db1e2a08c705923e52e21ea2937458c487d6f964c7dbcdbe07684f4faf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y/bundle.json","state_url":"https://pith.science/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y/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":"2026-06-10T14:09:05Z","links":{"resolver":"https://pith.science/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y","bundle":"https://pith.science/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y/bundle.json","state":"https://pith.science/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UP6QXXSIDKM6TSFYOBVX7UR6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7UP6QXXSIDKM6TSFYOBVX7UR6Y","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":"0bfde37e9a47731c4290b5beeae63d3b0dbe33432c017850c17b81040de4b13b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T05:02:34Z","title_canon_sha256":"0ba45982fd8aac4c1c3e1d34462bfefd6a58015016f379a12bf04e6084df709c"},"schema_version":"1.0","source":{"id":"2605.14380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14380","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14380v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14380","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"7UP6QXXSIDKM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7UP6QXXSIDKM6TSF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7UP6QXXS","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5dd7b4db1e2a08c705923e52e21ea2937458c487d6f964c7dbcdbe07684f4faf","target":"graph","created_at":"2026-05-17T23:39:07Z","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":"Our method surpasses DMRS Co-Pilot, reaching an accuracy of 58.26% (+40.25%) and a macro-F1 of 24.62% (+15.99%), thereby establishing a strong baseline for psychologically grounded defense mechanism classification in low-resource settings."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That synthetic examples generated by prompting with defense-mechanism definitions maintain sufficient psychological fidelity to improve downstream classification without introducing artifacts or label noise."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A context-aware synthetic augmentation framework with a hybrid clinical-language model improves psychological defense mechanism classification to 58.26% accuracy and 24.62% macro-F1 in low-resource conditions, outperforming the DMRS Co-Pilot baseline."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Context-aware synthetic augmentation with hybrid modeling lifts psychological defense mechanism classification to 58.26% accuracy under data scarcity."}],"snapshot_sha256":"283e7a063c9ffd2d29752dee4694636243aae8f26fae933c86a6e08e65071284"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Psychological defense mechanisms (PDMs) are unconscious cognitive processes that modulate how individuals perceive and respond to emotional distress. Automatically classifying PDMs from text is clinically valuable but severely hindered by data scarcity and class imbalance, challenges which generative augmentation alone cannot resolve without psychological grounding. In this work, we address these challenges in the PsyDefDetect shared task (BioNLP@ACL 2026) by proposing a context-aware synthetic augmentation framework combined with a hybrid classification model. Our hybrid model integrates cont","authors_text":"Hoang-Thuy-Duong Vu, Huy-Hieu Pham, Quoc-Cuong Pham","cross_cats":[],"headline":"Context-aware synthetic augmentation with hybrid modeling lifts psychological defense mechanism classification to 58.26% accuracy under data scarcity.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T05:02:34Z","title":"Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation"},"references":{"count":40,"internal_anchors":0,"resolved_work":40,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"2024 , url =","work_id":"d51311f2-60b6-40bd-accd-d57ff34092cf","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Focal Loss for Dense Object Detection , year=","work_id":"a0889e1e-a3c0-4f1c-bf9c-ee77d24e2418","year":null},{"cited_arxiv_id":"","doi":"10.1145/3209978.3210080","is_internal_anchor":false,"ref_index":3,"title":"Texygen: A benchmarking platform for text generation models","work_id":"0423f1a3-61f7-42b2-96e9-4a7e00c4dcb0","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Supervised Multimodal Bitransformers for Classifying Images and Text , author=. 2020 , eprint=","work_id":"2c3d1df6-bd43-4a91-97f6-73bf25e5e5c3","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Educational and Psychological Measurement , year=","work_id":"79c59a9e-5727-4129-8764-d56d6f236ed4","year":null}],"snapshot_sha256":"d171be1211b9329c6272a1039d70b00492c0db98b02ac68d5b073148e4796904"},"source":{"id":"2605.14380","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:31:21.429442Z","id":"7bd0a031-8a1c-4d25-8a5c-ffadf9fe41f5","model_set":{"reader":"grok-4.3"},"one_line_summary":"A context-aware synthetic augmentation framework with a hybrid clinical-language model improves psychological defense mechanism classification to 58.26% accuracy and 24.62% macro-F1 in low-resource conditions, outperforming the DMRS Co-Pilot baseline.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Context-aware synthetic augmentation with hybrid modeling lifts psychological defense mechanism classification to 58.26% accuracy under data scarcity.","strongest_claim":"Our method surpasses DMRS Co-Pilot, reaching an accuracy of 58.26% (+40.25%) and a macro-F1 of 24.62% (+15.99%), thereby establishing a strong baseline for psychologically grounded defense mechanism classification in low-resource settings.","weakest_assumption":"That synthetic examples generated by prompting with defense-mechanism definitions maintain sufficient psychological fidelity to improve downstream classification without introducing artifacts or label noise."}},"verdict_id":"7bd0a031-8a1c-4d25-8a5c-ffadf9fe41f5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c18aacbb87840c230ee33b7d8d9e741f3f28d1cecab7a2d3d1db9c39c93123c1","target":"record","created_at":"2026-05-17T23:39:07Z","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":"0bfde37e9a47731c4290b5beeae63d3b0dbe33432c017850c17b81040de4b13b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T05:02:34Z","title_canon_sha256":"0ba45982fd8aac4c1c3e1d34462bfefd6a58015016f379a12bf04e6084df709c"},"schema_version":"1.0","source":{"id":"2605.14380","kind":"arxiv","version":1}},"canonical_sha256":"fd1fe85ef240d4cf4e45c3835bfe91f600e63492dde99b315ec404b1c86643a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1fe85ef240d4cf4e45c3835bfe91f600e63492dde99b315ec404b1c86643a4","first_computed_at":"2026-05-17T23:39:07.734629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.734629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bMjPJ9D6hSRb0Gdil7gl7I1OXx3ljiU87mtZa2W6NvUiXvXsCbZA6GOxUh1hMYwy038y/wy/sM3ygKadM+JxDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.735337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c18aacbb87840c230ee33b7d8d9e741f3f28d1cecab7a2d3d1db9c39c93123c1","sha256:5dd7b4db1e2a08c705923e52e21ea2937458c487d6f964c7dbcdbe07684f4faf"],"state_sha256":"5271300eb61b2796f337769bee1b61d43e9e3979c0ab3b6d3174be31458fba58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HM/kgUCWM4GCUkwdhCmSZBNdhXLb/HoErTXKoWq67rRA4AK71ruGqcZH5/6O9uqhxWL60p/MClheTI6by+LBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T14:09:05.420280Z","bundle_sha256":"c1e6d374854f78164f14919b9fabdb110619da915946569bdb9fb15d9c6ee623"}}