{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I4AGASXOBC3CCB2FGL2NCMWPHA","short_pith_number":"pith:I4AGASXO","schema_version":"1.0","canonical_sha256":"4700604aee08b621074532f4d132cf3833940906e9e76541e5d03d78d59fce6f","source":{"kind":"arxiv","id":"2204.03418","version":1},"attestation_state":"computed","paper":{"title":"Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandros Iosifidis, Lukas Hedegaard","submitted_at":"2022-04-07T13:03:09Z","abstract_excerpt":"We present Continual Inference, a Python library for implementing Continual Inference Networks (CINs) in PyTorch, a class of Neural Networks designed specifically for efficient inference in both online and batch processing scenarios. We offer a comprehensive introduction and guide to CINs and their implementation in practice, and provide best-practices and code examples for composing complex modules for modern Deep Learning. Continual Inference is readily downloadable via the Python Package Index and at \\url{www.github.com/lukashedegaard/continual-inference}."},"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":"2204.03418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-07T13:03:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fb4f6276592f8c1d1c7aafa4c1f33b893fbba69fc5e305a04b0bdbd04143cf23","abstract_canon_sha256":"6e513425de2b9ae1b0d984c2c8d7874e5fdfc0fa7009017e08bc48140080c7ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:43.702787Z","signature_b64":"zFJGhbsaaSGcVu12vCerElUib+BofX4enPPYAW8PFABLb6zzPRdAC7uYBZWcSz5zEvHQo7iC015HfqqR4b9OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4700604aee08b621074532f4d132cf3833940906e9e76541e5d03d78d59fce6f","last_reissued_at":"2026-07-05T06:24:43.702437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:43.702437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandros Iosifidis, Lukas Hedegaard","submitted_at":"2022-04-07T13:03:09Z","abstract_excerpt":"We present Continual Inference, a Python library for implementing Continual Inference Networks (CINs) in PyTorch, a class of Neural Networks designed specifically for efficient inference in both online and batch processing scenarios. We offer a comprehensive introduction and guide to CINs and their implementation in practice, and provide best-practices and code examples for composing complex modules for modern Deep Learning. Continual Inference is readily downloadable via the Python Package Index and at \\url{www.github.com/lukashedegaard/continual-inference}."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03418","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/2204.03418/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":"2204.03418","created_at":"2026-07-05T06:24:43.702496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03418v1","created_at":"2026-07-05T06:24:43.702496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03418","created_at":"2026-07-05T06:24:43.702496+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4AGASXOBC3C","created_at":"2026-07-05T06:24:43.702496+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4AGASXOBC3CCB2F","created_at":"2026-07-05T06:24:43.702496+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4AGASXO","created_at":"2026-07-05T06:24:43.702496+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/I4AGASXOBC3CCB2FGL2NCMWPHA","json":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA.json","graph_json":"https://pith.science/api/pith-number/I4AGASXOBC3CCB2FGL2NCMWPHA/graph.json","events_json":"https://pith.science/api/pith-number/I4AGASXOBC3CCB2FGL2NCMWPHA/events.json","paper":"https://pith.science/paper/I4AGASXO"},"agent_actions":{"view_html":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA","download_json":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA.json","view_paper":"https://pith.science/paper/I4AGASXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03418&json=true","fetch_graph":"https://pith.science/api/pith-number/I4AGASXOBC3CCB2FGL2NCMWPHA/graph.json","fetch_events":"https://pith.science/api/pith-number/I4AGASXOBC3CCB2FGL2NCMWPHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA/action/storage_attestation","attest_author":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA/action/author_attestation","sign_citation":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA/action/citation_signature","submit_replication":"https://pith.science/pith/I4AGASXOBC3CCB2FGL2NCMWPHA/action/replication_record"}},"created_at":"2026-07-05T06:24:43.702496+00:00","updated_at":"2026-07-05T06:24:43.702496+00:00"}