{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CKWGWFVXI3RN2RAWOV6V2QHJSC","short_pith_number":"pith:CKWGWFVX","schema_version":"1.0","canonical_sha256":"12ac6b16b746e2dd4416757d5d40e990b7bb87b0e0c6a3ee1d81b48690f1391c","source":{"kind":"arxiv","id":"2203.11009","version":2},"attestation_state":"computed","paper":{"title":"Continual Spatio-Temporal Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Iosifidis, Lukas Hedegaard, Negar Heidari","submitted_at":"2022-03-21T14:23:18Z","abstract_excerpt":"Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the setting of online inference entails considerable computational redundancy. In this paper, we tackle this issue by reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network, which can perform step-by-step predictions in time without repeat frame processing. To evaluate our method, we create a continual version of ST-GC"},"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":"2203.11009","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-21T14:23:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc44c049162f3d7f134e782dbf01902c0b2cef0d4374af29011baeae51bf9d5f","abstract_canon_sha256":"f23ade7ed27cf71e6ef94e668da8a5e9030e4e4a8d47602acec8661bf84f0471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:11.591192Z","signature_b64":"tt2OygwWmlhL+AwdGOJOgJnT8vemGfswSfuNQajpqeutiQlzEVoPOy09fQ0o2gRayIdqOiOV1H1hwzx3HCPYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ac6b16b746e2dd4416757d5d40e990b7bb87b0e0c6a3ee1d81b48690f1391c","last_reissued_at":"2026-07-05T05:54:11.590752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:11.590752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Spatio-Temporal Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Iosifidis, Lukas Hedegaard, Negar Heidari","submitted_at":"2022-03-21T14:23:18Z","abstract_excerpt":"Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the setting of online inference entails considerable computational redundancy. In this paper, we tackle this issue by reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network, which can perform step-by-step predictions in time without repeat frame processing. To evaluate our method, we create a continual version of ST-GC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11009","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/2203.11009/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":"2203.11009","created_at":"2026-07-05T05:54:11.590808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11009v2","created_at":"2026-07-05T05:54:11.590808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11009","created_at":"2026-07-05T05:54:11.590808+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKWGWFVXI3RN","created_at":"2026-07-05T05:54:11.590808+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKWGWFVXI3RN2RAW","created_at":"2026-07-05T05:54:11.590808+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKWGWFVX","created_at":"2026-07-05T05:54:11.590808+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/CKWGWFVXI3RN2RAWOV6V2QHJSC","json":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC.json","graph_json":"https://pith.science/api/pith-number/CKWGWFVXI3RN2RAWOV6V2QHJSC/graph.json","events_json":"https://pith.science/api/pith-number/CKWGWFVXI3RN2RAWOV6V2QHJSC/events.json","paper":"https://pith.science/paper/CKWGWFVX"},"agent_actions":{"view_html":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC","download_json":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC.json","view_paper":"https://pith.science/paper/CKWGWFVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11009&json=true","fetch_graph":"https://pith.science/api/pith-number/CKWGWFVXI3RN2RAWOV6V2QHJSC/graph.json","fetch_events":"https://pith.science/api/pith-number/CKWGWFVXI3RN2RAWOV6V2QHJSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC/action/storage_attestation","attest_author":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC/action/author_attestation","sign_citation":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC/action/citation_signature","submit_replication":"https://pith.science/pith/CKWGWFVXI3RN2RAWOV6V2QHJSC/action/replication_record"}},"created_at":"2026-07-05T05:54:11.590808+00:00","updated_at":"2026-07-05T05:54:11.590808+00:00"}