{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LKEH3FG5JMEMLA6N2CCBHTBCLT","short_pith_number":"pith:LKEH3FG5","canonical_record":{"source":{"id":"2606.07502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:54:32Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"87e11d527bbe2ab13605fd3d065be2e2b1dcacf44a570d553b135239541bf7b1","abstract_canon_sha256":"9aab13584c9958f9c6d2f4e119b2657a22e0a7e7913f4f7f1b47175d8e8c5a0c"},"schema_version":"1.0"},"canonical_sha256":"5a887d94dd4b08c583cdd08413cc225cdb63f132ea7c40dcbb69d2bc6a5cb804","source":{"kind":"arxiv","id":"2606.07502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07502","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07502v1","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07502","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"LKEH3FG5JMEM","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"LKEH3FG5JMEMLA6N","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"LKEH3FG5","created_at":"2026-06-08T01:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LKEH3FG5JMEMLA6N2CCBHTBCLT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:54:32Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"87e11d527bbe2ab13605fd3d065be2e2b1dcacf44a570d553b135239541bf7b1","abstract_canon_sha256":"9aab13584c9958f9c6d2f4e119b2657a22e0a7e7913f4f7f1b47175d8e8c5a0c"},"schema_version":"1.0"},"canonical_sha256":"5a887d94dd4b08c583cdd08413cc225cdb63f132ea7c40dcbb69d2bc6a5cb804","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:31.368291Z","signature_b64":"qZ7cnCFq3xo14WX4ox4Zpt0cFE1eUlJVVA+OQk5Rtg4z9suJ2GFeT4MMCQrLvVsMdUgq3KIdUbkkIzl/2dIsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a887d94dd4b08c583cdd08413cc225cdb63f132ea7c40dcbb69d2bc6a5cb804","last_reissued_at":"2026-06-08T01:05:31.367184Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:31.367184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07502","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":"2026-06-08T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fd8fD4fR6BFKwpV3rZfLN5Pl7uyDRLEqkIMRM35D69tAYgM66l7YkgVl02GDzI84JtfTiNN2qSNMarIVG6QkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T23:40:57.085171Z"},"content_sha256":"6aad6dde79112a7a0a8b2902feb30cf8692f87a7dddf5579c7a09a74592043e6","schema_version":"1.0","event_id":"sha256:6aad6dde79112a7a0a8b2902feb30cf8692f87a7dddf5579c7a09a74592043e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LKEH3FG5JMEMLA6N2CCBHTBCLT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Cong Li, Heng Cui, Rui Yan, Songhao Wu, Yuxuan Liu, Zhongxin Chen","submitted_at":"2026-06-05T17:54:32Z","abstract_excerpt":"Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlying this deficiency. Our motivation stems from an unexpected observation: text embeddings tend to align with frequent but uninformative tokens when projected onto the vocabulary space. We argue that this excessive expression of high-frequency tokens suppresses the model's ability to capture nuanced s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07502","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/2606.07502/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":"2026-06-08T01:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMo9rsxzwQpb1eFLmzzXAZRqfvVImIKXu2F+jpOdTz1riqh+8SkBFdV7uB76zdAJkDQqhi+DGqJxtW6ffBRDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T23:40:57.085587Z"},"content_sha256":"6e9b03bd1611365ea8ab55d0d8463fbe4720c36091d40bb50c8e6f1cf2e36c4a","schema_version":"1.0","event_id":"sha256:6e9b03bd1611365ea8ab55d0d8463fbe4720c36091d40bb50c8e6f1cf2e36c4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT/bundle.json","state_url":"https://pith.science/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT/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":"2026-06-25T23:40:57Z","links":{"resolver":"https://pith.science/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT","bundle":"https://pith.science/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT/bundle.json","state":"https://pith.science/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKEH3FG5JMEMLA6N2CCBHTBCLT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LKEH3FG5JMEMLA6N2CCBHTBCLT","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":"9aab13584c9958f9c6d2f4e119b2657a22e0a7e7913f4f7f1b47175d8e8c5a0c","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:54:32Z","title_canon_sha256":"87e11d527bbe2ab13605fd3d065be2e2b1dcacf44a570d553b135239541bf7b1"},"schema_version":"1.0","source":{"id":"2606.07502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07502","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07502v1","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07502","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"LKEH3FG5JMEM","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"LKEH3FG5JMEMLA6N","created_at":"2026-06-08T01:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"LKEH3FG5","created_at":"2026-06-08T01:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:6e9b03bd1611365ea8ab55d0d8463fbe4720c36091d40bb50c8e6f1cf2e36c4a","target":"graph","created_at":"2026-06-08T01:05:31Z","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/2606.07502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlying this deficiency. Our motivation stems from an unexpected observation: text embeddings tend to align with frequent but uninformative tokens when projected onto the vocabulary space. We argue that this excessive expression of high-frequency tokens suppresses the model's ability to capture nuanced s","authors_text":"Cong Li, Heng Cui, Rui Yan, Songhao Wu, Yuxuan Liu, Zhongxin Chen","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:54:32Z","title":"Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07502","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":"sha256:6aad6dde79112a7a0a8b2902feb30cf8692f87a7dddf5579c7a09a74592043e6","target":"record","created_at":"2026-06-08T01:05:31Z","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":"9aab13584c9958f9c6d2f4e119b2657a22e0a7e7913f4f7f1b47175d8e8c5a0c","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T17:54:32Z","title_canon_sha256":"87e11d527bbe2ab13605fd3d065be2e2b1dcacf44a570d553b135239541bf7b1"},"schema_version":"1.0","source":{"id":"2606.07502","kind":"arxiv","version":1}},"canonical_sha256":"5a887d94dd4b08c583cdd08413cc225cdb63f132ea7c40dcbb69d2bc6a5cb804","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a887d94dd4b08c583cdd08413cc225cdb63f132ea7c40dcbb69d2bc6a5cb804","first_computed_at":"2026-06-08T01:05:31.367184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:31.367184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qZ7cnCFq3xo14WX4ox4Zpt0cFE1eUlJVVA+OQk5Rtg4z9suJ2GFeT4MMCQrLvVsMdUgq3KIdUbkkIzl/2dIsDA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:31.368291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aad6dde79112a7a0a8b2902feb30cf8692f87a7dddf5579c7a09a74592043e6","sha256:6e9b03bd1611365ea8ab55d0d8463fbe4720c36091d40bb50c8e6f1cf2e36c4a"],"state_sha256":"f5481c10add6558ded3219a69059123cbe1d456aeac5789c36eee3d2af47e848"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0K+qtNVkWM/vB363SQ+P9jXFqG8Zxtv0RWdD8rIO/fRyfNAE7spzQ25R+BCBc9SwDSTsOaPLw2psuZgQZcYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T23:40:57.087644Z","bundle_sha256":"55d4acf9d7c025f30f23d60555690a08d6f3137cddfa1cdbebf09d2d5e494aaf"}}