{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KJ7FU6QHVR4VG6VE4DMAJJX43K","short_pith_number":"pith:KJ7FU6QH","canonical_record":{"source":{"id":"2606.23642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T17:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"8b1e5549b8250d2b35a1bae3c13a60287f89d0800afe8fb5b0be7f32a289151a","abstract_canon_sha256":"65f9aa2193ba2dfbd147bff41f6249c377fa1eadb48a745c48c2423faa716b1b"},"schema_version":"1.0"},"canonical_sha256":"527e5a7a07ac79537aa4e0d804a6fcda94070c49f97a564b9273f6ee4215dd6e","source":{"kind":"arxiv","id":"2606.23642","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23642","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23642v1","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23642","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"KJ7FU6QHVR4V","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"KJ7FU6QHVR4VG6VE","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"KJ7FU6QH","created_at":"2026-06-23T03:14:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KJ7FU6QHVR4VG6VE4DMAJJX43K","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T17:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"8b1e5549b8250d2b35a1bae3c13a60287f89d0800afe8fb5b0be7f32a289151a","abstract_canon_sha256":"65f9aa2193ba2dfbd147bff41f6249c377fa1eadb48a745c48c2423faa716b1b"},"schema_version":"1.0"},"canonical_sha256":"527e5a7a07ac79537aa4e0d804a6fcda94070c49f97a564b9273f6ee4215dd6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:33.109731Z","signature_b64":"pWRBSdq83hf5ynGWnfpkBoQFp2Q6ImQifLQtae/hAwBRaxM690FGBLDdck9lzTj8iA6qqJlkpl92Ugoitu1wDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"527e5a7a07ac79537aa4e0d804a6fcda94070c49f97a564b9273f6ee4215dd6e","last_reissued_at":"2026-06-23T03:14:33.109303Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:33.109303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23642","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1OLm+939+KDb1yTLX3ILdoFtr4W4U7NbaVo51W6ZrR+yvVf50WBdoeoyhrjPRzVeA24Aruiup/BJ5OfZIF3JBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T21:46:55.863503Z"},"content_sha256":"4a92d38eac1e9e329bc0aa67f8520827d06b798da5ab99acf81bfade72574683","schema_version":"1.0","event_id":"sha256:4a92d38eac1e9e329bc0aa67f8520827d06b798da5ab99acf81bfade72574683"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KJ7FU6QHVR4VG6VE4DMAJJX43K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Long-Context Retrieval with Multi-Prefix Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Crystina Zhang, Jimmy Lin, Luyu Gao, Shengyao Zhuang, Xueguang Ma, Zhenglin Yu, Zhichao Xu","submitted_at":"2026-06-22T17:31:02Z","abstract_excerpt":"Long-context retrieval exposes a tension: single-vector embeddings lose fine-grained detail, while token-level multi-vector methods incur prohibitive storage. We propose Multi-Prefix Embedding (MPE), which partitions a document into chunks separated by EOS tokens, encodes the full sequence in a single causal forward pass, and extracts one embedding at each prefix boundary. MPE retains cross-chunk context, enables chunk-level MaxSim matching, and trains with only document-level relevance labels. Experiments on MLDR-en, BrowseComp-Plus, and LongEmbed show that MPE is competitive with or outperfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23642","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/2606.23642/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":"2026-06-23T03:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8e+azGfN5yJKsOOBqCUY1mHFdh6N6Y/PSGdR1q8zttwDWsjxBXp5KZCYLjvwARX38eMg9G8vYepWTx+ji0xfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T21:46:55.863874Z"},"content_sha256":"efab4f252284c12dac5e70abd637cc807bc36f00571832acf1a90bf5e53be208","schema_version":"1.0","event_id":"sha256:efab4f252284c12dac5e70abd637cc807bc36f00571832acf1a90bf5e53be208"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K/bundle.json","state_url":"https://pith.science/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K/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":"2026-06-26T21:46:55Z","links":{"resolver":"https://pith.science/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K","bundle":"https://pith.science/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K/bundle.json","state":"https://pith.science/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJ7FU6QHVR4VG6VE4DMAJJX43K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KJ7FU6QHVR4VG6VE4DMAJJX43K","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":"65f9aa2193ba2dfbd147bff41f6249c377fa1eadb48a745c48c2423faa716b1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T17:31:02Z","title_canon_sha256":"8b1e5549b8250d2b35a1bae3c13a60287f89d0800afe8fb5b0be7f32a289151a"},"schema_version":"1.0","source":{"id":"2606.23642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23642","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23642v1","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23642","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"KJ7FU6QHVR4V","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"KJ7FU6QHVR4VG6VE","created_at":"2026-06-23T03:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"KJ7FU6QH","created_at":"2026-06-23T03:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:efab4f252284c12dac5e70abd637cc807bc36f00571832acf1a90bf5e53be208","target":"graph","created_at":"2026-06-23T03:14:33Z","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/2606.23642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-context retrieval exposes a tension: single-vector embeddings lose fine-grained detail, while token-level multi-vector methods incur prohibitive storage. We propose Multi-Prefix Embedding (MPE), which partitions a document into chunks separated by EOS tokens, encodes the full sequence in a single causal forward pass, and extracts one embedding at each prefix boundary. MPE retains cross-chunk context, enables chunk-level MaxSim matching, and trains with only document-level relevance labels. Experiments on MLDR-en, BrowseComp-Plus, and LongEmbed show that MPE is competitive with or outperfo","authors_text":"Crystina Zhang, Jimmy Lin, Luyu Gao, Shengyao Zhuang, Xueguang Ma, Zhenglin Yu, Zhichao Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T17:31:02Z","title":"Improving Long-Context Retrieval with Multi-Prefix Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23642","kind":"arxiv","version":1},"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":"sha256:4a92d38eac1e9e329bc0aa67f8520827d06b798da5ab99acf81bfade72574683","target":"record","created_at":"2026-06-23T03:14:33Z","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":"65f9aa2193ba2dfbd147bff41f6249c377fa1eadb48a745c48c2423faa716b1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T17:31:02Z","title_canon_sha256":"8b1e5549b8250d2b35a1bae3c13a60287f89d0800afe8fb5b0be7f32a289151a"},"schema_version":"1.0","source":{"id":"2606.23642","kind":"arxiv","version":1}},"canonical_sha256":"527e5a7a07ac79537aa4e0d804a6fcda94070c49f97a564b9273f6ee4215dd6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"527e5a7a07ac79537aa4e0d804a6fcda94070c49f97a564b9273f6ee4215dd6e","first_computed_at":"2026-06-23T03:14:33.109303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:33.109303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pWRBSdq83hf5ynGWnfpkBoQFp2Q6ImQifLQtae/hAwBRaxM690FGBLDdck9lzTj8iA6qqJlkpl92Ugoitu1wDg==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:33.109731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a92d38eac1e9e329bc0aa67f8520827d06b798da5ab99acf81bfade72574683","sha256:efab4f252284c12dac5e70abd637cc807bc36f00571832acf1a90bf5e53be208"],"state_sha256":"d2f6efd26cec2e573c74f22e4feb6fe6f8d16bec572e33a88fa09900f8b96439"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IDBrmJ+tYYZ+OqVja0lldN2/egvs5H9NWfhzDy4kxibeAlbmJzlUk8zbGwMB5RB3jlVuDEqKB30whZmafriwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T21:46:55.865837Z","bundle_sha256":"b3d9c6ca896650d6f1f4247483b39e7e3434f8617dfe011e79ac2f3b830937a2"}}