{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:V2API2P2EEPW5AUQTOHMT2YOEG","short_pith_number":"pith:V2API2P2","schema_version":"1.0","canonical_sha256":"ae80f469fa211f6e82909b8ec9eb0e21b1c566a676f0a0907d2a980bb684bfaf","source":{"kind":"arxiv","id":"1704.08068","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Feedforward Artificial Neural Network Model From the Perspective of Network Flow","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dawei Dai, Hong Zhan, Weimin Tan","submitted_at":"2017-04-26T11:45:05Z","abstract_excerpt":"In recent years, deep learning based on artificial neural network (ANN) has achieved great success in pattern recognition. However, there is no clear understanding of such neural computational models. In this paper, we try to unravel \"black-box\" structure of Ann model from network flow. Specifically, we consider the feed forward Ann as a network flow model, which consists of many directional class-pathways. Each class-pathway encodes one class. The class-pathway of a class is obtained by connecting the activated neural nodes in each layer from input to output, where activation value of neural "},"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":"1704.08068","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-26T11:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"4e50f496a7a432c9613b1aba99464f1b32b3293f3d52e3220c4eba0696e21242","abstract_canon_sha256":"b016fc6e1246d5875d339f8bdf611d25226b39895db3886c22d52eeab5d8fbcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:31.195410Z","signature_b64":"OTeWh+REglV+KskjRHjQOdbr9hfnJ9Djxwf4S7EddwwKxm0PhN36vWBxTrw2lgKsd9kr/M/R4+Y4DfVw6yUrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae80f469fa211f6e82909b8ec9eb0e21b1c566a676f0a0907d2a980bb684bfaf","last_reissued_at":"2026-05-18T00:45:31.195026Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:31.195026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Feedforward Artificial Neural Network Model From the Perspective of Network Flow","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dawei Dai, Hong Zhan, Weimin Tan","submitted_at":"2017-04-26T11:45:05Z","abstract_excerpt":"In recent years, deep learning based on artificial neural network (ANN) has achieved great success in pattern recognition. However, there is no clear understanding of such neural computational models. In this paper, we try to unravel \"black-box\" structure of Ann model from network flow. Specifically, we consider the feed forward Ann as a network flow model, which consists of many directional class-pathways. Each class-pathway encodes one class. The class-pathway of a class is obtained by connecting the activated neural nodes in each layer from input to output, where activation value of neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08068","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":"1704.08068","created_at":"2026-05-18T00:45:31.195080+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.08068v1","created_at":"2026-05-18T00:45:31.195080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08068","created_at":"2026-05-18T00:45:31.195080+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2API2P2EEPW","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2API2P2EEPW5AUQ","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2API2P2","created_at":"2026-05-18T12:31:49.984773+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/V2API2P2EEPW5AUQTOHMT2YOEG","json":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG.json","graph_json":"https://pith.science/api/pith-number/V2API2P2EEPW5AUQTOHMT2YOEG/graph.json","events_json":"https://pith.science/api/pith-number/V2API2P2EEPW5AUQTOHMT2YOEG/events.json","paper":"https://pith.science/paper/V2API2P2"},"agent_actions":{"view_html":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG","download_json":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG.json","view_paper":"https://pith.science/paper/V2API2P2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.08068&json=true","fetch_graph":"https://pith.science/api/pith-number/V2API2P2EEPW5AUQTOHMT2YOEG/graph.json","fetch_events":"https://pith.science/api/pith-number/V2API2P2EEPW5AUQTOHMT2YOEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG/action/storage_attestation","attest_author":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG/action/author_attestation","sign_citation":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG/action/citation_signature","submit_replication":"https://pith.science/pith/V2API2P2EEPW5AUQTOHMT2YOEG/action/replication_record"}},"created_at":"2026-05-18T00:45:31.195080+00:00","updated_at":"2026-05-18T00:45:31.195080+00:00"}