{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BKVCYYZ5H4PPNBTHEEEQOMH3M4","short_pith_number":"pith:BKVCYYZ5","schema_version":"1.0","canonical_sha256":"0aaa2c633d3f1ef6866721090730fb670489029697cf0e010254177ae86c0b96","source":{"kind":"arxiv","id":"2009.13747","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Slicing for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Xiangqun Chen, Yao Guo, Yuanchun Li, Yunxin Liu, Ziqi Zhang","submitted_at":"2020-09-29T03:28:31Z","abstract_excerpt":"Program slicing has been widely applied in a variety of software engineering tasks. However, existing program slicing techniques only deal with traditional programs that are constructed with instructions and variables, rather than neural networks that are composed of neurons and synapses. In this paper, we propose NNSlicer, the first approach for slicing deep neural networks based on data flow analysis. Our method understands the reaction of each neuron to an input based on the difference between its behavior activated by the input and the average behavior over the whole dataset. Then we quant"},"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":"2009.13747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-09-29T03:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"f7770090f359a0ea457127e3a788d9dd698bb09914ddee6a680bb1af43fac5cb","abstract_canon_sha256":"8fe1c87ade64e92e10834bfb6c2164ebdfff6e0944757f6ff9c13af833f8b636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:44.573056Z","signature_b64":"x6o6X3vsajcMZgGnEiVLRoQijdL2+YP0qpqcBp7y4q2XTiNB/HEnfBSY/dzl2+5i1hu7YCAdETai1mr8qdTxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aaa2c633d3f1ef6866721090730fb670489029697cf0e010254177ae86c0b96","last_reissued_at":"2026-07-05T01:38:44.572709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:44.572709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Slicing for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Xiangqun Chen, Yao Guo, Yuanchun Li, Yunxin Liu, Ziqi Zhang","submitted_at":"2020-09-29T03:28:31Z","abstract_excerpt":"Program slicing has been widely applied in a variety of software engineering tasks. However, existing program slicing techniques only deal with traditional programs that are constructed with instructions and variables, rather than neural networks that are composed of neurons and synapses. In this paper, we propose NNSlicer, the first approach for slicing deep neural networks based on data flow analysis. Our method understands the reaction of each neuron to an input based on the difference between its behavior activated by the input and the average behavior over the whole dataset. Then we quant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13747","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/2009.13747/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2009.13747","created_at":"2026-07-05T01:38:44.572768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13747v1","created_at":"2026-07-05T01:38:44.572768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13747","created_at":"2026-07-05T01:38:44.572768+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKVCYYZ5H4PP","created_at":"2026-07-05T01:38:44.572768+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKVCYYZ5H4PPNBTH","created_at":"2026-07-05T01:38:44.572768+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKVCYYZ5","created_at":"2026-07-05T01:38:44.572768+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/BKVCYYZ5H4PPNBTHEEEQOMH3M4","json":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4.json","graph_json":"https://pith.science/api/pith-number/BKVCYYZ5H4PPNBTHEEEQOMH3M4/graph.json","events_json":"https://pith.science/api/pith-number/BKVCYYZ5H4PPNBTHEEEQOMH3M4/events.json","paper":"https://pith.science/paper/BKVCYYZ5"},"agent_actions":{"view_html":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4","download_json":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4.json","view_paper":"https://pith.science/paper/BKVCYYZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13747&json=true","fetch_graph":"https://pith.science/api/pith-number/BKVCYYZ5H4PPNBTHEEEQOMH3M4/graph.json","fetch_events":"https://pith.science/api/pith-number/BKVCYYZ5H4PPNBTHEEEQOMH3M4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4/action/storage_attestation","attest_author":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4/action/author_attestation","sign_citation":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4/action/citation_signature","submit_replication":"https://pith.science/pith/BKVCYYZ5H4PPNBTHEEEQOMH3M4/action/replication_record"}},"created_at":"2026-07-05T01:38:44.572768+00:00","updated_at":"2026-07-05T01:38:44.572768+00:00"}