{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PXABIWBFMDTJTKDLQZCTBBI2LQ","short_pith_number":"pith:PXABIWBF","canonical_record":{"source":{"id":"1908.05601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T12:57:26Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"d1a070b9ae712c40d22d32f85bd772daa61a00cd111bf74c3e380e3c0df3b443","abstract_canon_sha256":"a1b50d3d5be097038f7cc1b573619c31fd3d137839dfe4d6ad0c2b0f7ce0098d"},"schema_version":"1.0"},"canonical_sha256":"7dc014582560e699a86b864530851a5c1da9f58b99ff624504513e3a19287c53","source":{"kind":"arxiv","id":"1908.05601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05601","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05601v1","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05601","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"PXABIWBFMDTJ","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"PXABIWBFMDTJTKDL","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"PXABIWBF","created_at":"2026-07-04T23:56:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PXABIWBFMDTJTKDLQZCTBBI2LQ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.05601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T12:57:26Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"d1a070b9ae712c40d22d32f85bd772daa61a00cd111bf74c3e380e3c0df3b443","abstract_canon_sha256":"a1b50d3d5be097038f7cc1b573619c31fd3d137839dfe4d6ad0c2b0f7ce0098d"},"schema_version":"1.0"},"canonical_sha256":"7dc014582560e699a86b864530851a5c1da9f58b99ff624504513e3a19287c53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:54.250412Z","signature_b64":"Y7HDptCcxOCVjFrKJVp+6utPghCLcqyL1U4UcOdxTowcCs/pzF0D/NPLCbQday5x3SHDvaXscCwP9zvn5tf+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc014582560e699a86b864530851a5c1da9f58b99ff624504513e3a19287c53","last_reissued_at":"2026-07-04T23:56:54.249942Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:54.249942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.05601","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":"2026-07-04T23:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IqdpdmeM8KtwAxpTyVG7TNTLywZVWJLg1/erGmze6a9dtht92NDfi8PL/c4oF2eS8CX7Q3sX3v1q5l2SZccCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:49:00.426404Z"},"content_sha256":"5c2870ef49ab4d5e913c32fbf405ff11a332600a0fdb526b0359a60cb0f556e2","schema_version":"1.0","event_id":"sha256:5c2870ef49ab4d5e913c32fbf405ff11a332600a0fdb526b0359a60cb0f556e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PXABIWBFMDTJTKDLQZCTBBI2LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Credible Deep Neural Networks with Rationale Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Yang, Mengnan Du, Ninghao Liu, Xia Hu","submitted_at":"2019-08-13T12:57:26Z","abstract_excerpt":"Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In pursuit of developing more credible DNNs, in this paper we propose CREX, which encourages DNN models to focus more on evidences that actually matter for the task at hand, and to avoid overfitting to data-dependent bias and artifacts. Specifically, CREX regularizes the training process of DNNs with rationales, i.e., a subset of features highlighted by domain exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05601","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/1908.05601/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":"2026-07-04T23:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jlHIszASPG+mVSETfsoYq53FvIyrFjlHP0Eb2v6qVUfCmxPD0ZwwyX0ES3DTirO0+StppOQHPQnGHMk6wr/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:49:00.427177Z"},"content_sha256":"702ff49fdb37e91635bd531d7239346c43b0f332ce5c5e2035a6d29170590785","schema_version":"1.0","event_id":"sha256:702ff49fdb37e91635bd531d7239346c43b0f332ce5c5e2035a6d29170590785"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ/bundle.json","state_url":"https://pith.science/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ/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":"2026-08-16T11:49:00Z","links":{"resolver":"https://pith.science/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ","bundle":"https://pith.science/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ/bundle.json","state":"https://pith.science/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXABIWBFMDTJTKDLQZCTBBI2LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PXABIWBFMDTJTKDLQZCTBBI2LQ","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":"a1b50d3d5be097038f7cc1b573619c31fd3d137839dfe4d6ad0c2b0f7ce0098d","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T12:57:26Z","title_canon_sha256":"d1a070b9ae712c40d22d32f85bd772daa61a00cd111bf74c3e380e3c0df3b443"},"schema_version":"1.0","source":{"id":"1908.05601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05601","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05601v1","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05601","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"PXABIWBFMDTJ","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"PXABIWBFMDTJTKDL","created_at":"2026-07-04T23:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"PXABIWBF","created_at":"2026-07-04T23:56:54Z"}],"graph_snapshots":[{"event_id":"sha256:702ff49fdb37e91635bd531d7239346c43b0f332ce5c5e2035a6d29170590785","target":"graph","created_at":"2026-07-04T23:56:54Z","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/1908.05601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In pursuit of developing more credible DNNs, in this paper we propose CREX, which encourages DNN models to focus more on evidences that actually matter for the task at hand, and to avoid overfitting to data-dependent bias and artifacts. Specifically, CREX regularizes the training process of DNNs with rationales, i.e., a subset of features highlighted by domain exp","authors_text":"Fan Yang, Mengnan Du, Ninghao Liu, Xia Hu","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T12:57:26Z","title":"Learning Credible Deep Neural Networks with Rationale Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05601","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":"sha256:5c2870ef49ab4d5e913c32fbf405ff11a332600a0fdb526b0359a60cb0f556e2","target":"record","created_at":"2026-07-04T23:56:54Z","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":"a1b50d3d5be097038f7cc1b573619c31fd3d137839dfe4d6ad0c2b0f7ce0098d","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-13T12:57:26Z","title_canon_sha256":"d1a070b9ae712c40d22d32f85bd772daa61a00cd111bf74c3e380e3c0df3b443"},"schema_version":"1.0","source":{"id":"1908.05601","kind":"arxiv","version":1}},"canonical_sha256":"7dc014582560e699a86b864530851a5c1da9f58b99ff624504513e3a19287c53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dc014582560e699a86b864530851a5c1da9f58b99ff624504513e3a19287c53","first_computed_at":"2026-07-04T23:56:54.249942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:56:54.249942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y7HDptCcxOCVjFrKJVp+6utPghCLcqyL1U4UcOdxTowcCs/pzF0D/NPLCbQday5x3SHDvaXscCwP9zvn5tf+Ag==","signature_status":"signed_v1","signed_at":"2026-07-04T23:56:54.250412Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c2870ef49ab4d5e913c32fbf405ff11a332600a0fdb526b0359a60cb0f556e2","sha256:702ff49fdb37e91635bd531d7239346c43b0f332ce5c5e2035a6d29170590785"],"state_sha256":"12405fbb8755079091dcf20f22fd9568e00b8c07113d1c0ab269992a2ff3a56d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oRbgRA9jXWA0FNiQJVE8fAhVLWylPWf7Y1E96uZ/wXHJgKBxI7IoECcZ/+e+BV88klFusHlEFM7bZ419xkVNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T11:49:00.439123Z","bundle_sha256":"aa0014bc8c8fa0c635197a5df31908aaa78a292cc5263b8e86eeb38a8fd96f23"}}