{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EYNTY45MEASIHILYCZOJNOUAGL","short_pith_number":"pith:EYNTY45M","schema_version":"1.0","canonical_sha256":"261b3c73ac202483a178165c96ba8032e3aebfbc5aabf8650f5da17403313ab1","source":{"kind":"arxiv","id":"2502.01659","version":2},"attestation_state":"computed","paper":{"title":"Longer Attention Span: Increasing Transformer Context Length with Sparse Graph Processing Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.PF"],"primary_cat":"cs.LG","authors_text":"Nathaniel Tomczak, Sanmukh Kuppannagari","submitted_at":"2025-01-31T22:05:00Z","abstract_excerpt":"Transformers have demonstrated great success in numerous domains including natural language processing and bioinformatics. This success stems from the use of the attention mechanism by these models in order to represent and propagate pairwise interactions between individual tokens of sequential data. However, the primary limitation of this operation is its quadratic memory and time complexity in relation to the input's context length - the length of a sequence over which the interactions need to be captured. This significantly limits the length of sequences that can be inferred upon by these m"},"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":"2502.01659","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T22:05:00Z","cross_cats_sorted":["cs.AI","cs.DC","cs.PF"],"title_canon_sha256":"9137cdcbd6616b2fbdc242faee07d559707bb5c28420801324be2c1d8a48f2c8","abstract_canon_sha256":"3e5278282ff572ea6109389b11d131c78eda1cd3b59b79c3d86f6e6aed089963"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:49.011465Z","signature_b64":"xEk1y6fiwuVoC9CXErYabW3q37EzQDjratDBeUiPqi0iuz9fO2jqPAEF7Gb8JWJ2u4Zj2Z2d+606YhsUeR4UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261b3c73ac202483a178165c96ba8032e3aebfbc5aabf8650f5da17403313ab1","last_reissued_at":"2026-07-05T10:10:49.010995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:49.010995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Longer Attention Span: Increasing Transformer Context Length with Sparse Graph Processing Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.PF"],"primary_cat":"cs.LG","authors_text":"Nathaniel Tomczak, Sanmukh Kuppannagari","submitted_at":"2025-01-31T22:05:00Z","abstract_excerpt":"Transformers have demonstrated great success in numerous domains including natural language processing and bioinformatics. This success stems from the use of the attention mechanism by these models in order to represent and propagate pairwise interactions between individual tokens of sequential data. However, the primary limitation of this operation is its quadratic memory and time complexity in relation to the input's context length - the length of a sequence over which the interactions need to be captured. This significantly limits the length of sequences that can be inferred upon by these m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01659","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/2502.01659/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":"2502.01659","created_at":"2026-07-05T10:10:49.011051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01659v2","created_at":"2026-07-05T10:10:49.011051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01659","created_at":"2026-07-05T10:10:49.011051+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYNTY45MEASI","created_at":"2026-07-05T10:10:49.011051+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYNTY45MEASIHILY","created_at":"2026-07-05T10:10:49.011051+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYNTY45M","created_at":"2026-07-05T10:10:49.011051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10855","citing_title":"Sparse Fine-Tuning of Transformers for Generative Tasks","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL","json":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL.json","graph_json":"https://pith.science/api/pith-number/EYNTY45MEASIHILYCZOJNOUAGL/graph.json","events_json":"https://pith.science/api/pith-number/EYNTY45MEASIHILYCZOJNOUAGL/events.json","paper":"https://pith.science/paper/EYNTY45M"},"agent_actions":{"view_html":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL","download_json":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL.json","view_paper":"https://pith.science/paper/EYNTY45M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01659&json=true","fetch_graph":"https://pith.science/api/pith-number/EYNTY45MEASIHILYCZOJNOUAGL/graph.json","fetch_events":"https://pith.science/api/pith-number/EYNTY45MEASIHILYCZOJNOUAGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL/action/storage_attestation","attest_author":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL/action/author_attestation","sign_citation":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL/action/citation_signature","submit_replication":"https://pith.science/pith/EYNTY45MEASIHILYCZOJNOUAGL/action/replication_record"}},"created_at":"2026-07-05T10:10:49.011051+00:00","updated_at":"2026-07-05T10:10:49.011051+00:00"}