{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CJONTSUJ7NH2A5EWSNV5O57DMH","short_pith_number":"pith:CJONTSUJ","schema_version":"1.0","canonical_sha256":"125cd9ca89fb4fa07496936bd777e361d2b2684f0ee42e0a6d331f873010dc5e","source":{"kind":"arxiv","id":"1908.01581","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Consistency between Neural Networks and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing Wang, Longfei Li, Quanshi Zhang, Ruofan Liang, Tianlin Li","submitted_at":"2019-08-05T12:25:37Z","abstract_excerpt":"This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from raw intermediate-layer features of each neural network. As a generic tool, our method can be broadly used for different applications. In preliminary experiments, we have used knowledge consistency as a tool to diagnose representations of neural networks. Knowledge consistency pr"},"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":"1908.01581","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-05T12:25:37Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"bc81555a1028e2953efdcf2b720cbf11b886454ccd427c7674fe4d620ed3a341","abstract_canon_sha256":"8b4926c5952c6d049f2671bb42d57ec478d6c1f008bce6370536652752a6f1d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:14.855436Z","signature_b64":"oD89W3ZDbogQq8TSsJghSe6aT0nLjDJRvyzzOfcrHOc0yVsgBnuNiip/btHuOgsP6Fd/VJJFEzGN83YsIMNbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125cd9ca89fb4fa07496936bd777e361d2b2684f0ee42e0a6d331f873010dc5e","last_reissued_at":"2026-07-05T00:33:14.854998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:14.854998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Consistency between Neural Networks and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing Wang, Longfei Li, Quanshi Zhang, Ruofan Liang, Tianlin Li","submitted_at":"2019-08-05T12:25:37Z","abstract_excerpt":"This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from raw intermediate-layer features of each neural network. As a generic tool, our method can be broadly used for different applications. In preliminary experiments, we have used knowledge consistency as a tool to diagnose representations of neural networks. Knowledge consistency pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01581","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.01581/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":"1908.01581","created_at":"2026-07-05T00:33:14.855053+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01581v2","created_at":"2026-07-05T00:33:14.855053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01581","created_at":"2026-07-05T00:33:14.855053+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJONTSUJ7NH2","created_at":"2026-07-05T00:33:14.855053+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJONTSUJ7NH2A5EW","created_at":"2026-07-05T00:33:14.855053+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJONTSUJ","created_at":"2026-07-05T00:33:14.855053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.19361","citing_title":"We're Different, We're the Same: Creative Homogeneity Across LLMs","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH","json":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH.json","graph_json":"https://pith.science/api/pith-number/CJONTSUJ7NH2A5EWSNV5O57DMH/graph.json","events_json":"https://pith.science/api/pith-number/CJONTSUJ7NH2A5EWSNV5O57DMH/events.json","paper":"https://pith.science/paper/CJONTSUJ"},"agent_actions":{"view_html":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH","download_json":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH.json","view_paper":"https://pith.science/paper/CJONTSUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01581&json=true","fetch_graph":"https://pith.science/api/pith-number/CJONTSUJ7NH2A5EWSNV5O57DMH/graph.json","fetch_events":"https://pith.science/api/pith-number/CJONTSUJ7NH2A5EWSNV5O57DMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH/action/storage_attestation","attest_author":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH/action/author_attestation","sign_citation":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH/action/citation_signature","submit_replication":"https://pith.science/pith/CJONTSUJ7NH2A5EWSNV5O57DMH/action/replication_record"}},"created_at":"2026-07-05T00:33:14.855053+00:00","updated_at":"2026-07-05T00:33:14.855053+00:00"}