{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TTPOV2KET77JQELWHIWTRHFSQM","short_pith_number":"pith:TTPOV2KE","schema_version":"1.0","canonical_sha256":"9cdeeae9449ffe9811763a2d389cb28314baef479e2fa54581f1fab5564b8ddd","source":{"kind":"arxiv","id":"2508.03614","version":1},"attestation_state":"computed","paper":{"title":"Minimal Convolutional RNNs Accelerate Spatiotemporal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Co\\c{s}ku Can Horuz, Martin V. Butz, Matthias Karlbauer, Sebastian Otte","submitted_at":"2025-08-05T16:28:43Z","abstract_excerpt":"We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our approach extends the log-domain prefix-sum formulation of MinLSTM and MinGRU to convolutional architectures, enabling fully parallel training while retaining localized spatial modeling. This eliminates the need for sequential hidden state updates during teacher forcing - a major bottleneck in conventional ConvRNN models. In addition, we incorporate an exponential gating mechanism "},"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":"2508.03614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T16:28:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"0ebdd40aaf298aaf8d45d2eedc65fb8e4aa4f062096af3cb74c9f47bbb053bd2","abstract_canon_sha256":"96973dc47a683233866736184bde3a7b875230de3bed8e2febc097616e7ca5c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:59.935390Z","signature_b64":"yVRa4zHRKVWEPkCemqWSG5dleiOADXs0rg9g6q/07jiQt0TnNaY/eHOI7+PNro7BzXD854fX7xJg5Rp0OyTuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cdeeae9449ffe9811763a2d389cb28314baef479e2fa54581f1fab5564b8ddd","last_reissued_at":"2026-07-05T11:48:59.934916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:59.934916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimal Convolutional RNNs Accelerate Spatiotemporal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Co\\c{s}ku Can Horuz, Martin V. Butz, Matthias Karlbauer, Sebastian Otte","submitted_at":"2025-08-05T16:28:43Z","abstract_excerpt":"We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our approach extends the log-domain prefix-sum formulation of MinLSTM and MinGRU to convolutional architectures, enabling fully parallel training while retaining localized spatial modeling. This eliminates the need for sequential hidden state updates during teacher forcing - a major bottleneck in conventional ConvRNN models. In addition, we incorporate an exponential gating mechanism "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03614","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/2508.03614/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":"2508.03614","created_at":"2026-07-05T11:48:59.934973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03614v1","created_at":"2026-07-05T11:48:59.934973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03614","created_at":"2026-07-05T11:48:59.934973+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTPOV2KET77J","created_at":"2026-07-05T11:48:59.934973+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTPOV2KET77JQELW","created_at":"2026-07-05T11:48:59.934973+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTPOV2KE","created_at":"2026-07-05T11:48:59.934973+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/TTPOV2KET77JQELWHIWTRHFSQM","json":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM.json","graph_json":"https://pith.science/api/pith-number/TTPOV2KET77JQELWHIWTRHFSQM/graph.json","events_json":"https://pith.science/api/pith-number/TTPOV2KET77JQELWHIWTRHFSQM/events.json","paper":"https://pith.science/paper/TTPOV2KE"},"agent_actions":{"view_html":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM","download_json":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM.json","view_paper":"https://pith.science/paper/TTPOV2KE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03614&json=true","fetch_graph":"https://pith.science/api/pith-number/TTPOV2KET77JQELWHIWTRHFSQM/graph.json","fetch_events":"https://pith.science/api/pith-number/TTPOV2KET77JQELWHIWTRHFSQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM/action/storage_attestation","attest_author":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM/action/author_attestation","sign_citation":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM/action/citation_signature","submit_replication":"https://pith.science/pith/TTPOV2KET77JQELWHIWTRHFSQM/action/replication_record"}},"created_at":"2026-07-05T11:48:59.934973+00:00","updated_at":"2026-07-05T11:48:59.934973+00:00"}