{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Q54O4FUBCIM2F5JVFNTXF3QZAJ","short_pith_number":"pith:Q54O4FUB","schema_version":"1.0","canonical_sha256":"8778ee16811219a2f5352b6772ee19027a4e47a4c449323e403612ad096e3396","source":{"kind":"arxiv","id":"1811.02783","version":1},"attestation_state":"computed","paper":{"title":"YASENN: Explaining Neural Networks via Partitioning Activation Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tuzhilin, Denis Korzhenkov, Pavel Shvechikov, Yaroslav Zharov","submitted_at":"2018-11-07T07:35:45Z","abstract_excerpt":"We introduce a novel approach to feed-forward neural network interpretation based on partitioning the space of sequences of neuron activations. In line with this approach, we propose a model-specific interpretation method, called YASENN. Our method inherits many advantages of model-agnostic distillation, such as an ability to focus on the particular input region and to express an explanation in terms of features different from those observed by a neural network. Moreover, examination of distillation error makes the method applicable to the problems with low tolerance to interpretation mistakes"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1811.02783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-07T07:35:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1733dc10ea0b7a29fb01d0a42e050a76e648b6cfb640ed75876fed61aac4aada","abstract_canon_sha256":"d4115617bed7fe0b2b14511def0b10c5f25f5b8c390fff2754e129676925c5d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:20.796900Z","signature_b64":"kCrxxL6v/PxTmqRTPYTsiwWCiG33vhfL+spZ4BlvkFSmkiGWbQh/AhUvqcYjVSZo+S+hOrC9g700qgpHC+XdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8778ee16811219a2f5352b6772ee19027a4e47a4c449323e403612ad096e3396","last_reissued_at":"2026-05-18T00:01:20.796348Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:20.796348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YASENN: Explaining Neural Networks via Partitioning Activation Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tuzhilin, Denis Korzhenkov, Pavel Shvechikov, Yaroslav Zharov","submitted_at":"2018-11-07T07:35:45Z","abstract_excerpt":"We introduce a novel approach to feed-forward neural network interpretation based on partitioning the space of sequences of neuron activations. In line with this approach, we propose a model-specific interpretation method, called YASENN. Our method inherits many advantages of model-agnostic distillation, such as an ability to focus on the particular input region and to express an explanation in terms of features different from those observed by a neural network. Moreover, examination of distillation error makes the method applicable to the problems with low tolerance to interpretation mistakes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02783","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.02783","created_at":"2026-05-18T00:01:20.796444+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02783v1","created_at":"2026-05-18T00:01:20.796444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02783","created_at":"2026-05-18T00:01:20.796444+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q54O4FUBCIM2","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q54O4FUBCIM2F5JV","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q54O4FUB","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ","json":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ.json","graph_json":"https://pith.science/api/pith-number/Q54O4FUBCIM2F5JVFNTXF3QZAJ/graph.json","events_json":"https://pith.science/api/pith-number/Q54O4FUBCIM2F5JVFNTXF3QZAJ/events.json","paper":"https://pith.science/paper/Q54O4FUB"},"agent_actions":{"view_html":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ","download_json":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ.json","view_paper":"https://pith.science/paper/Q54O4FUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02783&json=true","fetch_graph":"https://pith.science/api/pith-number/Q54O4FUBCIM2F5JVFNTXF3QZAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q54O4FUBCIM2F5JVFNTXF3QZAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ/action/storage_attestation","attest_author":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ/action/author_attestation","sign_citation":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ/action/citation_signature","submit_replication":"https://pith.science/pith/Q54O4FUBCIM2F5JVFNTXF3QZAJ/action/replication_record"}},"created_at":"2026-05-18T00:01:20.796444+00:00","updated_at":"2026-05-18T00:01:20.796444+00:00"}