{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6B52CFUCSYZSA5PKN7NFNYUJF6","short_pith_number":"pith:6B52CFUC","schema_version":"1.0","canonical_sha256":"f07ba1168296332075ea6fda56e2892f9ff7a52737081bf17b3e2bb435962503","source":{"kind":"arxiv","id":"2212.05970","version":3},"attestation_state":"computed","paper":{"title":"Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Astha Singh, Breno Dantas Cruz, Fraol Batole, Hridesh Rajan, Rangeet Pan, Sayem Mohammad Imtiaz","submitted_at":"2022-12-09T03:29:38Z","abstract_excerpt":"Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions associated with the faulty behavior? Recent works on decomposing a fully connected neural network (FCNN) and convolutional neural network (CNN) into modules have shown the value of engineering deep models in this manner, which is standard in traditional SE but foreign for deep learning models. However, prior works focus on the image-based multiclass classifi"},"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":"2212.05970","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-12-09T03:29:38Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"345fb781d49088f1692df362aeef1aa0a8ae35536bb1ed3c7c040c8bb06a6ac7","abstract_canon_sha256":"f868a750ac76e9556a5102b3cc3aa0420ea19eb6822019a6d7aa00955e5918f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:10.297568Z","signature_b64":"BSJjnubv/aKuxJXujMc77a0IEbOsSbXuUe486BEW7NQExPj75YOI4SCWJdkVeijOSq9CGSj1Sex1xfN0dyFyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f07ba1168296332075ea6fda56e2892f9ff7a52737081bf17b3e2bb435962503","last_reissued_at":"2026-07-05T05:40:10.297105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:10.297105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Astha Singh, Breno Dantas Cruz, Fraol Batole, Hridesh Rajan, Rangeet Pan, Sayem Mohammad Imtiaz","submitted_at":"2022-12-09T03:29:38Z","abstract_excerpt":"Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions associated with the faulty behavior? Recent works on decomposing a fully connected neural network (FCNN) and convolutional neural network (CNN) into modules have shown the value of engineering deep models in this manner, which is standard in traditional SE but foreign for deep learning models. However, prior works focus on the image-based multiclass classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05970","kind":"arxiv","version":3},"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/2212.05970/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":"2212.05970","created_at":"2026-07-05T05:40:10.297172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05970v3","created_at":"2026-07-05T05:40:10.297172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05970","created_at":"2026-07-05T05:40:10.297172+00:00"},{"alias_kind":"pith_short_12","alias_value":"6B52CFUCSYZS","created_at":"2026-07-05T05:40:10.297172+00:00"},{"alias_kind":"pith_short_16","alias_value":"6B52CFUCSYZSA5PK","created_at":"2026-07-05T05:40:10.297172+00:00"},{"alias_kind":"pith_short_8","alias_value":"6B52CFUC","created_at":"2026-07-05T05:40:10.297172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18562","citing_title":"Deep Learning with Pretrained 'Internal World' Layers: A Gemma 3-Based Modular Architecture for Wildfire Prediction","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6","json":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6.json","graph_json":"https://pith.science/api/pith-number/6B52CFUCSYZSA5PKN7NFNYUJF6/graph.json","events_json":"https://pith.science/api/pith-number/6B52CFUCSYZSA5PKN7NFNYUJF6/events.json","paper":"https://pith.science/paper/6B52CFUC"},"agent_actions":{"view_html":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6","download_json":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6.json","view_paper":"https://pith.science/paper/6B52CFUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05970&json=true","fetch_graph":"https://pith.science/api/pith-number/6B52CFUCSYZSA5PKN7NFNYUJF6/graph.json","fetch_events":"https://pith.science/api/pith-number/6B52CFUCSYZSA5PKN7NFNYUJF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6/action/storage_attestation","attest_author":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6/action/author_attestation","sign_citation":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6/action/citation_signature","submit_replication":"https://pith.science/pith/6B52CFUCSYZSA5PKN7NFNYUJF6/action/replication_record"}},"created_at":"2026-07-05T05:40:10.297172+00:00","updated_at":"2026-07-05T05:40:10.297172+00:00"}