{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HWAJWGGC7WMCJGKTKZJ2G2TFWX","short_pith_number":"pith:HWAJWGGC","canonical_record":{"source":{"id":"2507.18171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:13:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"652d5afb2374118c94c2b65991f5252103f8090b978aab3ea15c6a54993e38d8","abstract_canon_sha256":"babf161b03dc8c095e6adda5c9f71651c03253ab7e8c5171e12cb2cc27b276f8"},"schema_version":"1.0"},"canonical_sha256":"3d809b18c2fd982499535653a36a65b5f18e1c194eb80a2a6f4c53408da5a146","source":{"kind":"arxiv","id":"2507.18171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18171","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18171v1","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18171","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"HWAJWGGC7WMC","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"HWAJWGGC7WMCJGKT","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"HWAJWGGC","created_at":"2026-07-05T11:42:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HWAJWGGC7WMCJGKTKZJ2G2TFWX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:13:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"652d5afb2374118c94c2b65991f5252103f8090b978aab3ea15c6a54993e38d8","abstract_canon_sha256":"babf161b03dc8c095e6adda5c9f71651c03253ab7e8c5171e12cb2cc27b276f8"},"schema_version":"1.0"},"canonical_sha256":"3d809b18c2fd982499535653a36a65b5f18e1c194eb80a2a6f4c53408da5a146","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:43.005274Z","signature_b64":"WEcdT4rGV5kDpWMAEJkI858XDVcPWkkUTfPijmNRN1hvtU91xJ1dRkmZkEZCB3DABfzxNhzrp3BkKRMnPTezBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d809b18c2fd982499535653a36a65b5f18e1c194eb80a2a6f4c53408da5a146","last_reissued_at":"2026-07-05T11:42:43.004786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:43.004786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18171","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":"2026-07-05T11:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uEzlOt3d5mWUmnGXdt0qinVIMHx+xRAGOsQyMklpR6WEtD4IEDysUJusO7TufiHlRh1nkcq9eOKZBlTkWc5YAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:18:22.393902Z"},"content_sha256":"0ef6065bdbb0ca8b63a85793539fa926e94d2e8745782c3411d04e2642eb11dc","schema_version":"1.0","event_id":"sha256:0ef6065bdbb0ca8b63a85793539fa926e94d2e8745782c3411d04e2642eb11dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HWAJWGGC7WMCJGKTKZJ2G2TFWX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongxia Wang, Haonan Zhang, Kexin Chen, Wenhai Wang, Yi Liu","submitted_at":"2025-07-24T08:13:16Z","abstract_excerpt":"Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, disrupting the normal distribution of embedding distances and degrading downstream performance. In this paper, we systematically investigate such anomalous tokens, formally defining them and introducing an efficient detection method, Sticky Token Detector (STD), based on sentence and token filtering. Applying STD to 40 checkpoints across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18171","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/2507.18171/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":"2026-07-05T11:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QnN+Og2TlIGrRtj154Nw9Ea6DurdPEbmHRC5iiCUElS4W2J0u1mo3aQkpfLfBg0rQlpPU5B5PivLV6cOlHSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:18:22.394405Z"},"content_sha256":"54881ec3de6c9be09199828c2bd964b8556a5fc4c5d7d82cb4ad5bdfde880161","schema_version":"1.0","event_id":"sha256:54881ec3de6c9be09199828c2bd964b8556a5fc4c5d7d82cb4ad5bdfde880161"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX/bundle.json","state_url":"https://pith.science/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX/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":"2026-08-09T17:18:22Z","links":{"resolver":"https://pith.science/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX","bundle":"https://pith.science/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX/bundle.json","state":"https://pith.science/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWAJWGGC7WMCJGKTKZJ2G2TFWX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HWAJWGGC7WMCJGKTKZJ2G2TFWX","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":"babf161b03dc8c095e6adda5c9f71651c03253ab7e8c5171e12cb2cc27b276f8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:13:16Z","title_canon_sha256":"652d5afb2374118c94c2b65991f5252103f8090b978aab3ea15c6a54993e38d8"},"schema_version":"1.0","source":{"id":"2507.18171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18171","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18171v1","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18171","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"HWAJWGGC7WMC","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"HWAJWGGC7WMCJGKT","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"HWAJWGGC","created_at":"2026-07-05T11:42:43Z"}],"graph_snapshots":[{"event_id":"sha256:54881ec3de6c9be09199828c2bd964b8556a5fc4c5d7d82cb4ad5bdfde880161","target":"graph","created_at":"2026-07-05T11:42:43Z","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/2507.18171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, disrupting the normal distribution of embedding distances and degrading downstream performance. In this paper, we systematically investigate such anomalous tokens, formally defining them and introducing an efficient detection method, Sticky Token Detector (STD), based on sentence and token filtering. Applying STD to 40 checkpoints across ","authors_text":"Dongxia Wang, Haonan Zhang, Kexin Chen, Wenhai Wang, Yi Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:13:16Z","title":"Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18171","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":"sha256:0ef6065bdbb0ca8b63a85793539fa926e94d2e8745782c3411d04e2642eb11dc","target":"record","created_at":"2026-07-05T11:42:43Z","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":"babf161b03dc8c095e6adda5c9f71651c03253ab7e8c5171e12cb2cc27b276f8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:13:16Z","title_canon_sha256":"652d5afb2374118c94c2b65991f5252103f8090b978aab3ea15c6a54993e38d8"},"schema_version":"1.0","source":{"id":"2507.18171","kind":"arxiv","version":1}},"canonical_sha256":"3d809b18c2fd982499535653a36a65b5f18e1c194eb80a2a6f4c53408da5a146","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d809b18c2fd982499535653a36a65b5f18e1c194eb80a2a6f4c53408da5a146","first_computed_at":"2026-07-05T11:42:43.004786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:43.004786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEcdT4rGV5kDpWMAEJkI858XDVcPWkkUTfPijmNRN1hvtU91xJ1dRkmZkEZCB3DABfzxNhzrp3BkKRMnPTezBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:43.005274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ef6065bdbb0ca8b63a85793539fa926e94d2e8745782c3411d04e2642eb11dc","sha256:54881ec3de6c9be09199828c2bd964b8556a5fc4c5d7d82cb4ad5bdfde880161"],"state_sha256":"c2c01e6d1d37136d044338db0f5153c39cbb9b8dc91b09d74524084833ef8ccf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iaDiu+wGmsEOwy7O40giHLc52Gw9fpeFmqGr1ar41/KI54RZ16AfsMbhPxQD03hdIqUarOE6GthwvY2NrHUDBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:18:22.398502Z","bundle_sha256":"63c0af7553635b8ee5d6aab0d21503a31b922de4411d3ac79b5a9f18c920c57b"}}