{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JJXCY2Z37YHCDVYMKQ77ZA6BL5","short_pith_number":"pith:JJXCY2Z3","canonical_record":{"source":{"id":"1811.03970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-08T18:23:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"283b9b0c5c8209f49d52ba4113d99c5d8df89cc9c853c8d051a2ce178d7d473e","abstract_canon_sha256":"bff8e9aa9eb22b2e5fb8d7da46ba7870f6bc0a68241ecf5228bc744c0f27fd35"},"schema_version":"1.0"},"canonical_sha256":"4a6e2c6b3bfe0e21d70c543ffc83c15f411eac91cb70b3e01edb1cae134c2af5","source":{"kind":"arxiv","id":"1811.03970","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03970","created_at":"2026-05-17T23:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03970v2","created_at":"2026-05-17T23:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03970","created_at":"2026-05-17T23:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"JJXCY2Z37YHC","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JJXCY2Z37YHCDVYM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JJXCY2Z3","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JJXCY2Z37YHCDVYMKQ77ZA6BL5","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03970","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-08T18:23:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"283b9b0c5c8209f49d52ba4113d99c5d8df89cc9c853c8d051a2ce178d7d473e","abstract_canon_sha256":"bff8e9aa9eb22b2e5fb8d7da46ba7870f6bc0a68241ecf5228bc744c0f27fd35"},"schema_version":"1.0"},"canonical_sha256":"4a6e2c6b3bfe0e21d70c543ffc83c15f411eac91cb70b3e01edb1cae134c2af5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:22.062238Z","signature_b64":"w5QUm30CRkb+B9b9bvRiLx/o15SPB/qPYNrCxorNZ9Wh+iFJZzW6+ZevOoYFuoL7L0xA6BaSXAepN4VrvTpkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a6e2c6b3bfe0e21d70c543ffc83c15f411eac91cb70b3e01edb1cae134c2af5","last_reissued_at":"2026-05-17T23:59:22.061848Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:22.061848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03970","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bABIE9eFRepYzIUbKcHGRHIYdSPLTpuI/d2ku9aAJzINsDqiQpWuJHQx766bHy7dFo3rxrijTT3pu+wutcU5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T01:52:59.962055Z"},"content_sha256":"ca82eb14ad0aa80e8ff646e4008548e4cd5531aedfe833f0714cca0248bf7688","schema_version":"1.0","event_id":"sha256:ca82eb14ad0aa80e8ff646e4008548e4cd5531aedfe833f0714cca0248bf7688"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JJXCY2Z37YHCDVYMKQ77ZA6BL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Looking Deeper into Deep Learning Model: Attribution-based Explanations of TextCNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Iftitahu Ni'mah, Jan Veldsink, Juan M. G. Huesca, Mykola Pechenizkiy, Wenting Xiong, Werner van Ipenburg","submitted_at":"2018-11-08T18:23:48Z","abstract_excerpt":"Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleting perturbation is a common evaluation method. This word removal approach, however, disregards any linguistic dependencies that may exist between words or phrases in a sentence, which could semantically guide a classifier to a particular prediction. In this paper, we present a fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03970","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KODnlyKUt7+zSYU2ZMdZ2dw1pzCbSbM+MysmNXd6th+8xKGGoH+rHs8PgG4wSull3zwIJ7PWrz5+/EP15DNmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T01:52:59.962778Z"},"content_sha256":"104d17d8ce4f8cb77afa9dc4782f76e901086e80bb091342018e0ff938e66f88","schema_version":"1.0","event_id":"sha256:104d17d8ce4f8cb77afa9dc4782f76e901086e80bb091342018e0ff938e66f88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5/bundle.json","state_url":"https://pith.science/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5/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":"2026-06-11T01:52:59Z","links":{"resolver":"https://pith.science/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5","bundle":"https://pith.science/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5/bundle.json","state":"https://pith.science/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJXCY2Z37YHCDVYMKQ77ZA6BL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JJXCY2Z37YHCDVYMKQ77ZA6BL5","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":"bff8e9aa9eb22b2e5fb8d7da46ba7870f6bc0a68241ecf5228bc744c0f27fd35","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-08T18:23:48Z","title_canon_sha256":"283b9b0c5c8209f49d52ba4113d99c5d8df89cc9c853c8d051a2ce178d7d473e"},"schema_version":"1.0","source":{"id":"1811.03970","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03970","created_at":"2026-05-17T23:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03970v2","created_at":"2026-05-17T23:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03970","created_at":"2026-05-17T23:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"JJXCY2Z37YHC","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JJXCY2Z37YHCDVYM","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JJXCY2Z3","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:104d17d8ce4f8cb77afa9dc4782f76e901086e80bb091342018e0ff938e66f88","target":"graph","created_at":"2026-05-17T23:59:22Z","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"},"paper":{"abstract_excerpt":"Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to highlight relevant words for a predicted class label, experiments based on word deleting perturbation is a common evaluation method. This word removal approach, however, disregards any linguistic dependencies that may exist between words or phrases in a sentence, which could semantically guide a classifier to a particular prediction. In this paper, we present a fe","authors_text":"Iftitahu Ni'mah, Jan Veldsink, Juan M. G. Huesca, Mykola Pechenizkiy, Wenting Xiong, Werner van Ipenburg","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-08T18:23:48Z","title":"Looking Deeper into Deep Learning Model: Attribution-based Explanations of TextCNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03970","kind":"arxiv","version":2},"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:ca82eb14ad0aa80e8ff646e4008548e4cd5531aedfe833f0714cca0248bf7688","target":"record","created_at":"2026-05-17T23:59:22Z","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":"bff8e9aa9eb22b2e5fb8d7da46ba7870f6bc0a68241ecf5228bc744c0f27fd35","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-08T18:23:48Z","title_canon_sha256":"283b9b0c5c8209f49d52ba4113d99c5d8df89cc9c853c8d051a2ce178d7d473e"},"schema_version":"1.0","source":{"id":"1811.03970","kind":"arxiv","version":2}},"canonical_sha256":"4a6e2c6b3bfe0e21d70c543ffc83c15f411eac91cb70b3e01edb1cae134c2af5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a6e2c6b3bfe0e21d70c543ffc83c15f411eac91cb70b3e01edb1cae134c2af5","first_computed_at":"2026-05-17T23:59:22.061848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:22.061848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w5QUm30CRkb+B9b9bvRiLx/o15SPB/qPYNrCxorNZ9Wh+iFJZzW6+ZevOoYFuoL7L0xA6BaSXAepN4VrvTpkAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:22.062238Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03970","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca82eb14ad0aa80e8ff646e4008548e4cd5531aedfe833f0714cca0248bf7688","sha256:104d17d8ce4f8cb77afa9dc4782f76e901086e80bb091342018e0ff938e66f88"],"state_sha256":"a1039cbeb4eeb1ffc5186c20f5521311ea11ae7bcedbab8409bdc1a3a988989c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqQX4jNqZ0fV8kAS+nG9o4grx2vjKcjPbIQ7Z5Hi65n1wyt+LfnxW4b1HGQk9GpQnx+S/rd6AqjSxf3MIGaqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T01:52:59.966996Z","bundle_sha256":"e3ffc1dbfc8469edee7ae5480e81f0b35579bff5c4922ecced82b9f0fa92b705"}}