{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WN2T6J77PVOQVGICMBEC5X2AOS","short_pith_number":"pith:WN2T6J77","schema_version":"1.0","canonical_sha256":"b3753f27ff7d5d0a990260482edf4074a09a107587e231a66f140fc9dadd545d","source":{"kind":"arxiv","id":"2406.09477","version":1},"attestation_state":"computed","paper":{"title":"Q-S5: Towards Quantized State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alessandro Pierro, Jens E. Pedersen, Kade M. Heckel, Steven Abreu","submitted_at":"2024-06-13T09:53:24Z","abstract_excerpt":"In the quest for next-generation sequence modeling architectures, State Space Models (SSMs) have emerged as a potent alternative to transformers, particularly for their computational efficiency and suitability for dynamical systems. This paper investigates the effect of quantization on the S5 model to understand its impact on model performance and to facilitate its deployment to edge and resource-constrained platforms. Using quantization-aware training (QAT) and post-training quantization (PTQ), we systematically evaluate the quantization sensitivity of SSMs across different tasks like dynamic"},"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":"2406.09477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T09:53:24Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"9d7cd77eaecaa809a60dfc9e1e1a19eed46fe770846704fac8d6cbf201295344","abstract_canon_sha256":"c74195be48499775f5d056a7c3a5c13ba81a1a2faae23b97f1a7861bd5bbdeeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:54.615128Z","signature_b64":"IbArpG7nT8SkJudFqOI0dWTrTqI2IFYSRg2yPvRr62bKCT49EXE6dC3f4FSEGjbWzAaQ1Y1CLJ6W1bG9yzaNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3753f27ff7d5d0a990260482edf4074a09a107587e231a66f140fc9dadd545d","last_reissued_at":"2026-07-05T08:31:54.614648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:54.614648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-S5: Towards Quantized State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alessandro Pierro, Jens E. Pedersen, Kade M. Heckel, Steven Abreu","submitted_at":"2024-06-13T09:53:24Z","abstract_excerpt":"In the quest for next-generation sequence modeling architectures, State Space Models (SSMs) have emerged as a potent alternative to transformers, particularly for their computational efficiency and suitability for dynamical systems. This paper investigates the effect of quantization on the S5 model to understand its impact on model performance and to facilitate its deployment to edge and resource-constrained platforms. Using quantization-aware training (QAT) and post-training quantization (PTQ), we systematically evaluate the quantization sensitivity of SSMs across different tasks like dynamic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09477","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/2406.09477/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":"2406.09477","created_at":"2026-07-05T08:31:54.614706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09477v1","created_at":"2026-07-05T08:31:54.614706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09477","created_at":"2026-07-05T08:31:54.614706+00:00"},{"alias_kind":"pith_short_12","alias_value":"WN2T6J77PVOQ","created_at":"2026-07-05T08:31:54.614706+00:00"},{"alias_kind":"pith_short_16","alias_value":"WN2T6J77PVOQVGIC","created_at":"2026-07-05T08:31:54.614706+00:00"},{"alias_kind":"pith_short_8","alias_value":"WN2T6J77","created_at":"2026-07-05T08:31:54.614706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06079","citing_title":"QS4D: Quantization-aware training for efficient hardware deployment of structured state-space sequential models","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS","json":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS.json","graph_json":"https://pith.science/api/pith-number/WN2T6J77PVOQVGICMBEC5X2AOS/graph.json","events_json":"https://pith.science/api/pith-number/WN2T6J77PVOQVGICMBEC5X2AOS/events.json","paper":"https://pith.science/paper/WN2T6J77"},"agent_actions":{"view_html":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS","download_json":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS.json","view_paper":"https://pith.science/paper/WN2T6J77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09477&json=true","fetch_graph":"https://pith.science/api/pith-number/WN2T6J77PVOQVGICMBEC5X2AOS/graph.json","fetch_events":"https://pith.science/api/pith-number/WN2T6J77PVOQVGICMBEC5X2AOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS/action/storage_attestation","attest_author":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS/action/author_attestation","sign_citation":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS/action/citation_signature","submit_replication":"https://pith.science/pith/WN2T6J77PVOQVGICMBEC5X2AOS/action/replication_record"}},"created_at":"2026-07-05T08:31:54.614706+00:00","updated_at":"2026-07-05T08:31:54.614706+00:00"}