{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CIC3KOK5ZYPDPL56N666PKSTSJ","short_pith_number":"pith:CIC3KOK5","canonical_record":{"source":{"id":"2511.20102","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-25T09:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"db899b5559af13d43aaf306dfcef496254f64d1a208a6c7146030a2e0884f0e4","abstract_canon_sha256":"290a15a6b6a82470e43928016ba97930829135faf72e4b6f8af2f58e8479d4c4"},"schema_version":"1.0"},"canonical_sha256":"1205b5395dce1e37afbe6fbde7aa53927f6919ee1badf980843ff61d5b431f83","source":{"kind":"arxiv","id":"2511.20102","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.20102","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"arxiv_version","alias_value":"2511.20102v3","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20102","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"pith_short_12","alias_value":"CIC3KOK5ZYPD","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"pith_short_16","alias_value":"CIC3KOK5ZYPDPL56","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"pith_short_8","alias_value":"CIC3KOK5","created_at":"2026-06-04T01:09:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CIC3KOK5ZYPDPL56N666PKSTSJ","target":"record","payload":{"canonical_record":{"source":{"id":"2511.20102","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-25T09:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"db899b5559af13d43aaf306dfcef496254f64d1a208a6c7146030a2e0884f0e4","abstract_canon_sha256":"290a15a6b6a82470e43928016ba97930829135faf72e4b6f8af2f58e8479d4c4"},"schema_version":"1.0"},"canonical_sha256":"1205b5395dce1e37afbe6fbde7aa53927f6919ee1badf980843ff61d5b431f83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:39.866217Z","signature_b64":"TcJXVD93CrdxCbcpJasokIOa9PE09Iw0gtkUwWztNCPKUNoYNRLiZxp4/1MsQPwLJb9yMwlfvLBFTDnwlV0nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1205b5395dce1e37afbe6fbde7aa53927f6919ee1badf980843ff61d5b431f83","last_reissued_at":"2026-06-04T01:09:39.865619Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:39.865619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.20102","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iYTyTitVy2Li4NfzApF8ZP8h0zAQM3k/e+sW89uz65kfaUbwzCPSSt3ePHW5/xiT8+haUcUkCd0FAUvScTWEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T21:27:31.566126Z"},"content_sha256":"56ab723e05849a6b42614c0fdca88c0a8d0ad2389dc29e09d532843d8812efcd","schema_version":"1.0","event_id":"sha256:56ab723e05849a6b42614c0fdca88c0a8d0ad2389dc29e09d532843d8812efcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CIC3KOK5ZYPDPL56N666PKSTSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Yin, Jiazheng Li, Junru Lu, Lin Gui, Xing Sun, Yulan He, Zhenyi Shen","submitted_at":"2025-11-25T09:21:57Z","abstract_excerpt":"Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained models causes performance degradation due to train-inference distribution mismatch, and (2) a capability gap, where models trained purely with sparse attention lack complete gradient flow, preventing them from matching full-attention performance. We propose SSA (Sparse Sparse Attention), a training framework that integrates both sparse and full attention with bidirectional attention-output alignment. We prove that the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20102","kind":"arxiv","version":3},"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/2511.20102/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KvS1e/kmvJSOVaG3PYqozQhqo06FYs+rXZo5hox7Hut1fCyKv0rmE9Z9Ky2B3HzGUc7jHdr1fvg7l8G86k81DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T21:27:31.566529Z"},"content_sha256":"de0bf1a0cce71d2f0dc54b9d98aecf359358c4ddb94388563811221c52c818f5","schema_version":"1.0","event_id":"sha256:de0bf1a0cce71d2f0dc54b9d98aecf359358c4ddb94388563811221c52c818f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIC3KOK5ZYPDPL56N666PKSTSJ/bundle.json","state_url":"https://pith.science/pith/CIC3KOK5ZYPDPL56N666PKSTSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIC3KOK5ZYPDPL56N666PKSTSJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T21:27:31Z","links":{"resolver":"https://pith.science/pith/CIC3KOK5ZYPDPL56N666PKSTSJ","bundle":"https://pith.science/pith/CIC3KOK5ZYPDPL56N666PKSTSJ/bundle.json","state":"https://pith.science/pith/CIC3KOK5ZYPDPL56N666PKSTSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIC3KOK5ZYPDPL56N666PKSTSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CIC3KOK5ZYPDPL56N666PKSTSJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"290a15a6b6a82470e43928016ba97930829135faf72e4b6f8af2f58e8479d4c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-25T09:21:57Z","title_canon_sha256":"db899b5559af13d43aaf306dfcef496254f64d1a208a6c7146030a2e0884f0e4"},"schema_version":"1.0","source":{"id":"2511.20102","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.20102","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"arxiv_version","alias_value":"2511.20102v3","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20102","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"pith_short_12","alias_value":"CIC3KOK5ZYPD","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"pith_short_16","alias_value":"CIC3KOK5ZYPDPL56","created_at":"2026-06-04T01:09:39Z"},{"alias_kind":"pith_short_8","alias_value":"CIC3KOK5","created_at":"2026-06-04T01:09:39Z"}],"graph_snapshots":[{"event_id":"sha256:de0bf1a0cce71d2f0dc54b9d98aecf359358c4ddb94388563811221c52c818f5","target":"graph","created_at":"2026-06-04T01:09:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.20102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained models causes performance degradation due to train-inference distribution mismatch, and (2) a capability gap, where models trained purely with sparse attention lack complete gradient flow, preventing them from matching full-attention performance. We propose SSA (Sparse Sparse Attention), a training framework that integrates both sparse and full attention with bidirectional attention-output alignment. We prove that the","authors_text":"Di Yin, Jiazheng Li, Junru Lu, Lin Gui, Xing Sun, Yulan He, Zhenyi Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-25T09:21:57Z","title":"SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20102","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:56ab723e05849a6b42614c0fdca88c0a8d0ad2389dc29e09d532843d8812efcd","target":"record","created_at":"2026-06-04T01:09:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"290a15a6b6a82470e43928016ba97930829135faf72e4b6f8af2f58e8479d4c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-25T09:21:57Z","title_canon_sha256":"db899b5559af13d43aaf306dfcef496254f64d1a208a6c7146030a2e0884f0e4"},"schema_version":"1.0","source":{"id":"2511.20102","kind":"arxiv","version":3}},"canonical_sha256":"1205b5395dce1e37afbe6fbde7aa53927f6919ee1badf980843ff61d5b431f83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1205b5395dce1e37afbe6fbde7aa53927f6919ee1badf980843ff61d5b431f83","first_computed_at":"2026-06-04T01:09:39.865619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:39.865619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TcJXVD93CrdxCbcpJasokIOa9PE09Iw0gtkUwWztNCPKUNoYNRLiZxp4/1MsQPwLJb9yMwlfvLBFTDnwlV0nAQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:39.866217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.20102","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56ab723e05849a6b42614c0fdca88c0a8d0ad2389dc29e09d532843d8812efcd","sha256:de0bf1a0cce71d2f0dc54b9d98aecf359358c4ddb94388563811221c52c818f5"],"state_sha256":"5b9e852205fd4f9bc348ca1f252a8777712d1e591302163313a70bef7f0e8ade"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zv2LxGD71Oz5wCz0J/oyj8/ZE0ave4M9mPyAoU7NB7n2cjouPf8anrkpOg5dss+Uts0Pg8S80jzkyoDvMJeYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T21:27:31.569738Z","bundle_sha256":"1c50f0ced1fb12c305f196cab8d002099e4974aef68466e00d01c920c6319065"}}