{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J5XZZZ2FACHM6WR5BPT4SO67EE","short_pith_number":"pith:J5XZZZ2F","schema_version":"1.0","canonical_sha256":"4f6f9ce745008ecf5a3d0be7c93bdf2133b2e60f22d2bdf681d6d39a943c0d84","source":{"kind":"arxiv","id":"2506.20810","version":1},"attestation_state":"computed","paper":{"title":"FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","eess.SP"],"primary_cat":"cs.LG","authors_text":"Jakoba Petri-Koenig, Michaela Blott, Shashwat Khandelwal, Shreejith Shanker, Thomas B. Preu{\\ss}er","submitted_at":"2025-06-25T20:07:46Z","abstract_excerpt":"Recurrent neural networks (RNNs), particularly LSTMs, are effective for time-series tasks like sentiment analysis and short-term stock prediction. However, their computational complexity poses challenges for real-time deployment in resource constrained environments. While FPGAs offer a promising platform for energy-efficient AI acceleration, existing tools mainly target feed-forward networks, and LSTM acceleration typically requires full custom implementation. In this paper, we address this gap by leveraging the open-source and extensible FINN framework to enable the generalized deployment of "},"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":"2506.20810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T20:07:46Z","cross_cats_sorted":["cs.AI","cs.AR","eess.SP"],"title_canon_sha256":"0a5a7c9d15b819c9bdb97bb116dd8f330e26f9aea1d258184f4ff42b13a122f1","abstract_canon_sha256":"1f1aefef70a007ea148a53547e60f16a3982bb279c45045b5e7542a5f02bc299"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:34.492899Z","signature_b64":"rzIuiXjVZan3Eejb6ACIIuqfoA5+GQ0kuXIb22ebFU+vlbsmDrLbWrzjieFDZF8RFTrMzZAhDLnu+c4vVjoACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f6f9ce745008ecf5a3d0be7c93bdf2133b2e60f22d2bdf681d6d39a943c0d84","last_reissued_at":"2026-07-05T11:27:34.492351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:34.492351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","eess.SP"],"primary_cat":"cs.LG","authors_text":"Jakoba Petri-Koenig, Michaela Blott, Shashwat Khandelwal, Shreejith Shanker, Thomas B. Preu{\\ss}er","submitted_at":"2025-06-25T20:07:46Z","abstract_excerpt":"Recurrent neural networks (RNNs), particularly LSTMs, are effective for time-series tasks like sentiment analysis and short-term stock prediction. However, their computational complexity poses challenges for real-time deployment in resource constrained environments. While FPGAs offer a promising platform for energy-efficient AI acceleration, existing tools mainly target feed-forward networks, and LSTM acceleration typically requires full custom implementation. In this paper, we address this gap by leveraging the open-source and extensible FINN framework to enable the generalized deployment of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20810","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/2506.20810/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":"2506.20810","created_at":"2026-07-05T11:27:34.492419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20810v1","created_at":"2026-07-05T11:27:34.492419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20810","created_at":"2026-07-05T11:27:34.492419+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5XZZZ2FACHM","created_at":"2026-07-05T11:27:34.492419+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5XZZZ2FACHM6WR5","created_at":"2026-07-05T11:27:34.492419+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5XZZZ2F","created_at":"2026-07-05T11:27:34.492419+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/J5XZZZ2FACHM6WR5BPT4SO67EE","json":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE.json","graph_json":"https://pith.science/api/pith-number/J5XZZZ2FACHM6WR5BPT4SO67EE/graph.json","events_json":"https://pith.science/api/pith-number/J5XZZZ2FACHM6WR5BPT4SO67EE/events.json","paper":"https://pith.science/paper/J5XZZZ2F"},"agent_actions":{"view_html":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE","download_json":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE.json","view_paper":"https://pith.science/paper/J5XZZZ2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20810&json=true","fetch_graph":"https://pith.science/api/pith-number/J5XZZZ2FACHM6WR5BPT4SO67EE/graph.json","fetch_events":"https://pith.science/api/pith-number/J5XZZZ2FACHM6WR5BPT4SO67EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE/action/storage_attestation","attest_author":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE/action/author_attestation","sign_citation":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE/action/citation_signature","submit_replication":"https://pith.science/pith/J5XZZZ2FACHM6WR5BPT4SO67EE/action/replication_record"}},"created_at":"2026-07-05T11:27:34.492419+00:00","updated_at":"2026-07-05T11:27:34.492419+00:00"}