{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5Z6UROOVIIVS5TRTCYKT6MBEBG","short_pith_number":"pith:5Z6UROOV","schema_version":"1.0","canonical_sha256":"ee7d48b9d5422b2ece3316153f30240991ce830f8361894ac4527310a6311cb5","source":{"kind":"arxiv","id":"2605.15913","version":1},"attestation_state":"computed","paper":{"title":"Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenlong Deng, Dongyang Ma, Lei Zhu, Shuaiyi Li, Wai Lam, Yang Deng, Yan Wang, Zhisong Zhang","submitted_at":"2026-05-15T12:51:32Z","abstract_excerpt":"Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained blocks, and the inefficiency of existing block fine-tuning methods that risk degrading performance. To address these, we first construct SemanticSeg, a large and diverse semantic segmentation dataset containing over 30k instances across"},"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":"2605.15913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T12:51:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d825b39d0d6666adfc336f32eedb169a149e94e7165a3bd2273cd412e2b780e","abstract_canon_sha256":"c9a8fcaca8cf15bf606017a820461cdb6ee041e13b75740244a2e92260e4b945"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:45.019504Z","signature_b64":"smdmIPu+Q1Amk0uGm7SnWLVluJ2CkCyAidyfsAJ+rUYCP6oROKFRjMeJ78Nz8OHloiQkvzvkUo+87NifSdC3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee7d48b9d5422b2ece3316153f30240991ce830f8361894ac4527310a6311cb5","last_reissued_at":"2026-05-20T00:01:45.018990Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:45.018990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenlong Deng, Dongyang Ma, Lei Zhu, Shuaiyi Li, Wai Lam, Yang Deng, Yan Wang, Zhisong Zhang","submitted_at":"2026-05-15T12:51:32Z","abstract_excerpt":"Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained blocks, and the inefficiency of existing block fine-tuning methods that risk degrading performance. To address these, we first construct SemanticSeg, a large and diverse semantic segmentation dataset containing over 30k instances across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15913","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/2605.15913/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:46.557099Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.760203Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f687a0b3f111ffafc9b05e1132859759ab92131e3cce634e63a54b98bf08022c"},"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":"2605.15913","created_at":"2026-05-20T00:01:45.019060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15913v1","created_at":"2026-05-20T00:01:45.019060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15913","created_at":"2026-05-20T00:01:45.019060+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z6UROOVIIVS","created_at":"2026-05-20T00:01:45.019060+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z6UROOVIIVS5TRT","created_at":"2026-05-20T00:01:45.019060+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z6UROOV","created_at":"2026-05-20T00:01:45.019060+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/5Z6UROOVIIVS5TRTCYKT6MBEBG","json":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG.json","graph_json":"https://pith.science/api/pith-number/5Z6UROOVIIVS5TRTCYKT6MBEBG/graph.json","events_json":"https://pith.science/api/pith-number/5Z6UROOVIIVS5TRTCYKT6MBEBG/events.json","paper":"https://pith.science/paper/5Z6UROOV"},"agent_actions":{"view_html":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG","download_json":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG.json","view_paper":"https://pith.science/paper/5Z6UROOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15913&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z6UROOVIIVS5TRTCYKT6MBEBG/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z6UROOVIIVS5TRTCYKT6MBEBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG/action/storage_attestation","attest_author":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG/action/author_attestation","sign_citation":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG/action/citation_signature","submit_replication":"https://pith.science/pith/5Z6UROOVIIVS5TRTCYKT6MBEBG/action/replication_record"}},"created_at":"2026-05-20T00:01:45.019060+00:00","updated_at":"2026-05-20T00:01:45.019060+00:00"}