{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KY56WKFDKOM57FEHX6ELAHQ6EP","short_pith_number":"pith:KY56WKFD","schema_version":"1.0","canonical_sha256":"563beb28a35399df9487bf88b01e1e23fa090bb49af53a1904031ac2edb7094f","source":{"kind":"arxiv","id":"2508.17679","version":1},"attestation_state":"computed","paper":{"title":"Characterizing the Behavior of Training Mamba-based State Space Models on GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR","cs.CL"],"primary_cat":"cs.LG","authors_text":"David Kaeli, Kaustubh Shivdikar, Sara Prescott, Trinayan Baruah","submitted_at":"2025-08-25T05:22:27Z","abstract_excerpt":"Mamba-based State Space Models (SSM) have emerged as a promising alternative to the ubiquitous transformers. Despite the expressive power of transformers, the quadratic complexity of computing attention is a major impediment to scaling performance as we increase the sequence length. SSMs provide an alternative path that addresses this problem, reducing the computational complexity requirements of self-attention with novel model architectures for different domains and fields such as video, text generation and graphs. Thus, it is important to characterize the behavior of these emerging workloads"},"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":"2508.17679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T05:22:27Z","cross_cats_sorted":["cs.AR","cs.CL"],"title_canon_sha256":"ae1c394e0097feb3ac3b93b896908292a9ca0c8a26d40e37e01f4e80b546a55f","abstract_canon_sha256":"be10a76124a3362437da270a2c523bed2cdd8bfe22e28c80d31fa5e165967d60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:45.689122Z","signature_b64":"YAfw2lnSpaG/WTfN6swbc2s9tnS/5l+j+Svg69PhogHubTaF4SsbR2WBtgxQhOkFmudyG1uKv5EGtoeh69LdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"563beb28a35399df9487bf88b01e1e23fa090bb49af53a1904031ac2edb7094f","last_reissued_at":"2026-07-05T11:58:45.688652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:45.688652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterizing the Behavior of Training Mamba-based State Space Models on GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR","cs.CL"],"primary_cat":"cs.LG","authors_text":"David Kaeli, Kaustubh Shivdikar, Sara Prescott, Trinayan Baruah","submitted_at":"2025-08-25T05:22:27Z","abstract_excerpt":"Mamba-based State Space Models (SSM) have emerged as a promising alternative to the ubiquitous transformers. Despite the expressive power of transformers, the quadratic complexity of computing attention is a major impediment to scaling performance as we increase the sequence length. SSMs provide an alternative path that addresses this problem, reducing the computational complexity requirements of self-attention with novel model architectures for different domains and fields such as video, text generation and graphs. Thus, it is important to characterize the behavior of these emerging workloads"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17679","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/2508.17679/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":"2508.17679","created_at":"2026-07-05T11:58:45.688710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17679v1","created_at":"2026-07-05T11:58:45.688710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17679","created_at":"2026-07-05T11:58:45.688710+00:00"},{"alias_kind":"pith_short_12","alias_value":"KY56WKFDKOM5","created_at":"2026-07-05T11:58:45.688710+00:00"},{"alias_kind":"pith_short_16","alias_value":"KY56WKFDKOM57FEH","created_at":"2026-07-05T11:58:45.688710+00:00"},{"alias_kind":"pith_short_8","alias_value":"KY56WKFD","created_at":"2026-07-05T11:58:45.688710+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/KY56WKFDKOM57FEHX6ELAHQ6EP","json":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP.json","graph_json":"https://pith.science/api/pith-number/KY56WKFDKOM57FEHX6ELAHQ6EP/graph.json","events_json":"https://pith.science/api/pith-number/KY56WKFDKOM57FEHX6ELAHQ6EP/events.json","paper":"https://pith.science/paper/KY56WKFD"},"agent_actions":{"view_html":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP","download_json":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP.json","view_paper":"https://pith.science/paper/KY56WKFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17679&json=true","fetch_graph":"https://pith.science/api/pith-number/KY56WKFDKOM57FEHX6ELAHQ6EP/graph.json","fetch_events":"https://pith.science/api/pith-number/KY56WKFDKOM57FEHX6ELAHQ6EP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP/action/storage_attestation","attest_author":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP/action/author_attestation","sign_citation":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP/action/citation_signature","submit_replication":"https://pith.science/pith/KY56WKFDKOM57FEHX6ELAHQ6EP/action/replication_record"}},"created_at":"2026-07-05T11:58:45.688710+00:00","updated_at":"2026-07-05T11:58:45.688710+00:00"}