{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A2VLS634G7NBPBZK7YSSVR4HQZ","short_pith_number":"pith:A2VLS634","canonical_record":{"source":{"id":"2605.21758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:40:44Z","cross_cats_sorted":[],"title_canon_sha256":"01b75aacc4782987a3509ec0dc50a66cdbe4588defa94efa66c3019860e3bd94","abstract_canon_sha256":"9086605ea23ff4363b8ef275adb438ac3443f8b9da1f306582a3a37ae6539aef"},"schema_version":"1.0"},"canonical_sha256":"06aab97b7c37da17872afe252ac7878668669e45a01e44045b3ca8888b6325db","source":{"kind":"arxiv","id":"2605.21758","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21758","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21758v1","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21758","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"A2VLS634G7NB","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"A2VLS634G7NBPBZK","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"A2VLS634","created_at":"2026-05-22T01:03:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A2VLS634G7NBPBZK7YSSVR4HQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.21758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:40:44Z","cross_cats_sorted":[],"title_canon_sha256":"01b75aacc4782987a3509ec0dc50a66cdbe4588defa94efa66c3019860e3bd94","abstract_canon_sha256":"9086605ea23ff4363b8ef275adb438ac3443f8b9da1f306582a3a37ae6539aef"},"schema_version":"1.0"},"canonical_sha256":"06aab97b7c37da17872afe252ac7878668669e45a01e44045b3ca8888b6325db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:30.753916Z","signature_b64":"u4+qT02cY1fyqSZgyvBE/EY7s0MuXVABmaj8Epm/m+q8yHMDz8lWlrgD9E7h9hwhA67YQ6rqjjP8/qjFrQuBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06aab97b7c37da17872afe252ac7878668669e45a01e44045b3ca8888b6325db","last_reissued_at":"2026-05-22T01:03:30.753257Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:30.753257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.21758","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":"2026-05-22T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1E1PKOOqh4BispWyNag+BtzRvz7G7DJW7OpsUZR4UVKe9gLjqt07AKwTJyNGlyzILTPIioHk1Rzz2VVFYpHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:31:54.193843Z"},"content_sha256":"3d7d480496c04657adb40040afaf291eb2ba789f137167362bea5aadf3169b77","schema_version":"1.0","event_id":"sha256:3d7d480496c04657adb40040afaf291eb2ba789f137167362bea5aadf3169b77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A2VLS634G7NBPBZK7YSSVR4HQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Causal Argumentation Method for Explainability of Machine Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Henry Salgado, Martine Ceberio, Meagan R. Kendall","submitted_at":"2026-05-20T21:40:44Z","abstract_excerpt":"Explainable AI (XAI) methods identify which features are relevant to a model's predictions but often fail to clarify why certain decisions are made. In this work, we present a novel method that integrates causality with argument-based reasoning to explain why models may be making predictions. Our approach first identifies causal relationships among variables using causal discovery methods and then translates these into a Bipolar Argumentation Framework (BAF) to represent supportive and opposing interactions among features. By using semi-stable semantics, we find extensions of features that exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21758","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/2605.21758/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":"2026-05-22T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v1okAqFQmi3O29KtfHfpjiJ6AJCChZRNF7ITEXjhWSx1sczpm/cuYeaet8VZBy0O/a1AtYfm2Ot/BivQ4AFtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:31:54.194243Z"},"content_sha256":"ec0b46d7f491937c5743b1fbb07d95c5b146b7fe4e9cee7d8451fd0f322a1552","schema_version":"1.0","event_id":"sha256:ec0b46d7f491937c5743b1fbb07d95c5b146b7fe4e9cee7d8451fd0f322a1552"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:A2VLS634G7NBPBZK7YSSVR4HQZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.3389/fgene.2019.00524/fullA) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Glymour, C., Zhang, K., Spirtes, P.: Review of Causal Discovery Methods Based on Graphical Models. Frontiers in Genetics10(Jun 2019).https://doi.org/10.3 389/fgene.2019.00524, https://www.frontiersin.org/journals/genetics/ar ticles/10.3389/","arxiv_id":"2605.21758","detector":"doi_compliance","evidence":{"ref_index":9,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Glymour, C., Zhang, K., Spirtes, P.: Review of Causal Discovery Methods Based on Graphical Models. Frontiers in Genetics10(Jun 2019).https://doi.org/10.3 389/fgene.2019.00524, https://www.frontiersin.org/journals/genetics/ar ticles/10.3389/","reconstructed_doi":"10.3389/fgene.2019.00524/fullA"},"severity":"advisory","ref_index":9,"audited_at":"2026-05-22T09:00:00.404714Z","event_type":"pith.integrity.v1","detected_doi":"10.3389/fgene.2019.00524/fullA","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"51935514b091ca6e09c35e499ca3022cd9be767ce935426376adf4f82ead24cd","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":6308,"payload_sha256":"eb3b85f80306cdfa45e1e0e4b56a2edca89f2f6663df3b520c8fa43987167c38","signature_b64":"FYGLsI+HfKssf+mkCuzIPu4WhnAsOQBdP8E8hhJA37uhp/4dgUvhYv0Wybzx8epU6sjdxyIo691tpqaKIxwIBg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T09:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMmgbfAGfM2dFQiwoZ7Kyi99eHoZOygnsMv0SQjtmOJ0elDYOFsvZ38y2Uzs8Jkqih9vA0IqzOO156S184aKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:31:54.195367Z"},"content_sha256":"ad33bdfa50eccb70a179f6db45a384dd6768a5fc6ce101de4c49a4e2c54fc709","schema_version":"1.0","event_id":"sha256:ad33bdfa50eccb70a179f6db45a384dd6768a5fc6ce101de4c49a4e2c54fc709"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:A2VLS634G7NBPBZK7YSSVR4HQZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1214/aos/1013203451.full) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Friedman, J.H.: Greedy function approximation: A gradient boosting machine. The Annals of Statistics29(5), 1189–1232 (Oct 2001).https://doi.org/10.1214/aos/ 1013203451, https://projecteuclid.org/journals/annals-of-statistics/vo lume-29/issu","arxiv_id":"2605.21758","detector":"doi_compliance","evidence":{"ref_index":8,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Friedman, J.H.: Greedy function approximation: A gradient boosting machine. The Annals of Statistics29(5), 1189–1232 (Oct 2001).https://doi.org/10.1214/aos/ 1013203451, https://projecteuclid.org/journals/annals-of-statistics/vo lume-29/issu","reconstructed_doi":"10.1214/aos/1013203451.full"},"severity":"advisory","ref_index":8,"audited_at":"2026-05-22T09:00:00.404714Z","event_type":"pith.integrity.v1","detected_doi":"10.1214/aos/1013203451.full","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"286cf2585a257399be1a6f5c58bb2055e7e9dead1fa7bb5e53979d6bed255d62","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":6307,"payload_sha256":"3acec928236946ed3a0a258e4afe44ef6f4e942a5370b784357770792ec8e3d4","signature_b64":"gIGtbQi827qjHfCCB4T7VmN0CotDM0rEYDMz9gdLmZPw5iaFvnKhyjEeicU1+U6NMkRo9FHgJupujEvU2iKsCw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T09:00:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MNOAi1LZi1Kb1yukhBv/JhhbwbT2spBoBVb9RV0uoB9ovt5ckskODHL5gRonk2Us3UdLDlDQLB8yFKBpXdCxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:31:54.195719Z"},"content_sha256":"0cc2d68fe90d95afeef2ad5b44ae4dda559cdc53a21147161e3257625b367b6e","schema_version":"1.0","event_id":"sha256:0cc2d68fe90d95afeef2ad5b44ae4dda559cdc53a21147161e3257625b367b6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2VLS634G7NBPBZK7YSSVR4HQZ/bundle.json","state_url":"https://pith.science/pith/A2VLS634G7NBPBZK7YSSVR4HQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2VLS634G7NBPBZK7YSSVR4HQZ/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":"2026-05-26T08:31:54Z","links":{"resolver":"https://pith.science/pith/A2VLS634G7NBPBZK7YSSVR4HQZ","bundle":"https://pith.science/pith/A2VLS634G7NBPBZK7YSSVR4HQZ/bundle.json","state":"https://pith.science/pith/A2VLS634G7NBPBZK7YSSVR4HQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2VLS634G7NBPBZK7YSSVR4HQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A2VLS634G7NBPBZK7YSSVR4HQZ","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9086605ea23ff4363b8ef275adb438ac3443f8b9da1f306582a3a37ae6539aef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:40:44Z","title_canon_sha256":"01b75aacc4782987a3509ec0dc50a66cdbe4588defa94efa66c3019860e3bd94"},"schema_version":"1.0","source":{"id":"2605.21758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21758","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21758v1","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21758","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"A2VLS634G7NB","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"A2VLS634G7NBPBZK","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"A2VLS634","created_at":"2026-05-22T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:ec0b46d7f491937c5743b1fbb07d95c5b146b7fe4e9cee7d8451fd0f322a1552","target":"graph","created_at":"2026-05-22T01:03:30Z","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/2605.21758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explainable AI (XAI) methods identify which features are relevant to a model's predictions but often fail to clarify why certain decisions are made. In this work, we present a novel method that integrates causality with argument-based reasoning to explain why models may be making predictions. Our approach first identifies causal relationships among variables using causal discovery methods and then translates these into a Bipolar Argumentation Framework (BAF) to represent supportive and opposing interactions among features. By using semi-stable semantics, we find extensions of features that exp","authors_text":"Henry Salgado, Martine Ceberio, Meagan R. Kendall","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:40:44Z","title":"A Causal Argumentation Method for Explainability of Machine Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21758","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":"sha256:3d7d480496c04657adb40040afaf291eb2ba789f137167362bea5aadf3169b77","target":"record","created_at":"2026-05-22T01:03:30Z","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":"9086605ea23ff4363b8ef275adb438ac3443f8b9da1f306582a3a37ae6539aef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-20T21:40:44Z","title_canon_sha256":"01b75aacc4782987a3509ec0dc50a66cdbe4588defa94efa66c3019860e3bd94"},"schema_version":"1.0","source":{"id":"2605.21758","kind":"arxiv","version":1}},"canonical_sha256":"06aab97b7c37da17872afe252ac7878668669e45a01e44045b3ca8888b6325db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06aab97b7c37da17872afe252ac7878668669e45a01e44045b3ca8888b6325db","first_computed_at":"2026-05-22T01:03:30.753257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:30.753257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u4+qT02cY1fyqSZgyvBE/EY7s0MuXVABmaj8Epm/m+q8yHMDz8lWlrgD9E7h9hwhA67YQ6rqjjP8/qjFrQuBCQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:30.753916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21758","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:0cc2d68fe90d95afeef2ad5b44ae4dda559cdc53a21147161e3257625b367b6e","sha256:ad33bdfa50eccb70a179f6db45a384dd6768a5fc6ce101de4c49a4e2c54fc709"]}],"invalid_events":[],"applied_event_ids":["sha256:3d7d480496c04657adb40040afaf291eb2ba789f137167362bea5aadf3169b77","sha256:ec0b46d7f491937c5743b1fbb07d95c5b146b7fe4e9cee7d8451fd0f322a1552"],"state_sha256":"63dd557b4a8cbfc25844af92947fc1be8427d3275c156c7c931e221e0e8a4412"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJDVNWxthyhRY7vV2sP++Rm8Su0Hv1mDJIw1ucAlSMHYcPG6lUCZux/3jTpTw0fMDph7aqHkRKbmo74XIecbCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:31:54.199076Z","bundle_sha256":"698875266576ab1ed9ba4143c389bde6eaa2aa068ce79b9fb7cfec9273f80bf7"}}