{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AUWAGAYWEFN6EBWPSPLLWU5ZNZ","short_pith_number":"pith:AUWAGAYW","canonical_record":{"source":{"id":"2410.24200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:36Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1a1d1f321175022af56a2a36aae9d2042442dde2e1dabe46c41eec95657d0b79","abstract_canon_sha256":"ef722561fa6a9b236ba63c123db3e34fb2609bd3eded2d25925f333b89568c08"},"schema_version":"1.0"},"canonical_sha256":"052c030316215be206cf93d6bb53b96e7b4e5c670028e1c9bf1cbfdee10476fe","source":{"kind":"arxiv","id":"2410.24200","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24200","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24200v2","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24200","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"AUWAGAYWEFN6","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"AUWAGAYWEFN6EBWP","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"AUWAGAYW","created_at":"2026-07-05T11:18:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AUWAGAYWEFN6EBWPSPLLWU5ZNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.24200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:36Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1a1d1f321175022af56a2a36aae9d2042442dde2e1dabe46c41eec95657d0b79","abstract_canon_sha256":"ef722561fa6a9b236ba63c123db3e34fb2609bd3eded2d25925f333b89568c08"},"schema_version":"1.0"},"canonical_sha256":"052c030316215be206cf93d6bb53b96e7b4e5c670028e1c9bf1cbfdee10476fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:40.110453Z","signature_b64":"udrcbsKPfuDu71a2tF9AZbotlRlmB38qMp+3uzEftljumLR6kwoQJFTN1aBk7Hyz+oCpGuv8jLDIaMwuVlKsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"052c030316215be206cf93d6bb53b96e7b4e5c670028e1c9bf1cbfdee10476fe","last_reissued_at":"2026-07-05T11:18:40.109970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:40.109970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.24200","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRKMGok8eT+jeEAPnRMOMKbab394qXTLET38VchJj2qpMVx62/YHxR8c3mzs4vIwxLCIFIEEohNaQiidqj6bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:35:48.794635Z"},"content_sha256":"acf0708ad078c3f976c5bab62eb2a4c9e243b5b654352263429528daa39205ef","schema_version":"1.0","event_id":"sha256:acf0708ad078c3f976c5bab62eb2a4c9e243b5b654352263429528daa39205ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AUWAGAYWEFN6EBWPSPLLWU5ZNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Length-Induced Embedding Collapse in PLM-based Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jun Xu, Sunhao Dai, Xiao Zhang, Yuqi Zhou, Zhanshuo Cao","submitted_at":"2024-10-31T17:55:36Z","abstract_excerpt":"Text embeddings from PLM-based models enable a wide range of applications, yet their performance often degrades on longer texts. In this paper, we introduce a phenomenon we call Length Collapse, where embeddings of longer texts tend to cluster together. This clustering results in a distributional inconsistency between the embeddings of short and long texts. We further investigate how these differences contribute to the performance decline observed with longer texts across various downstream tasks. Through a rigorous theoretical analysis of the self-attention mechanism, which acts as a low-pass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24200","kind":"arxiv","version":2},"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/2410.24200/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":"2026-07-05T11:18:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qLc9EWuJ8G9H+Ag1e3WaizK2GAu99icD3zqTWCoGu7YsvRJAt/DNvk3QuoascnYNWCx8ReliTLW/8jYlJ3AeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:35:48.795159Z"},"content_sha256":"ef18106ae6523b748d8455f18399dbaf17d02ee130ac0d89ff70ca4fa2153296","schema_version":"1.0","event_id":"sha256:ef18106ae6523b748d8455f18399dbaf17d02ee130ac0d89ff70ca4fa2153296"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ/bundle.json","state_url":"https://pith.science/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ/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":"2026-08-06T21:35:48Z","links":{"resolver":"https://pith.science/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ","bundle":"https://pith.science/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ/bundle.json","state":"https://pith.science/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AUWAGAYWEFN6EBWPSPLLWU5ZNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AUWAGAYWEFN6EBWPSPLLWU5ZNZ","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":"ef722561fa6a9b236ba63c123db3e34fb2609bd3eded2d25925f333b89568c08","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:36Z","title_canon_sha256":"1a1d1f321175022af56a2a36aae9d2042442dde2e1dabe46c41eec95657d0b79"},"schema_version":"1.0","source":{"id":"2410.24200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24200","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24200v2","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24200","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"AUWAGAYWEFN6","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"AUWAGAYWEFN6EBWP","created_at":"2026-07-05T11:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"AUWAGAYW","created_at":"2026-07-05T11:18:40Z"}],"graph_snapshots":[{"event_id":"sha256:ef18106ae6523b748d8455f18399dbaf17d02ee130ac0d89ff70ca4fa2153296","target":"graph","created_at":"2026-07-05T11:18:40Z","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/2410.24200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embeddings from PLM-based models enable a wide range of applications, yet their performance often degrades on longer texts. In this paper, we introduce a phenomenon we call Length Collapse, where embeddings of longer texts tend to cluster together. This clustering results in a distributional inconsistency between the embeddings of short and long texts. We further investigate how these differences contribute to the performance decline observed with longer texts across various downstream tasks. Through a rigorous theoretical analysis of the self-attention mechanism, which acts as a low-pass","authors_text":"Jun Xu, Sunhao Dai, Xiao Zhang, Yuqi Zhou, Zhanshuo Cao","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:36Z","title":"Length-Induced Embedding Collapse in PLM-based Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24200","kind":"arxiv","version":2},"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:acf0708ad078c3f976c5bab62eb2a4c9e243b5b654352263429528daa39205ef","target":"record","created_at":"2026-07-05T11:18:40Z","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":"ef722561fa6a9b236ba63c123db3e34fb2609bd3eded2d25925f333b89568c08","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T17:55:36Z","title_canon_sha256":"1a1d1f321175022af56a2a36aae9d2042442dde2e1dabe46c41eec95657d0b79"},"schema_version":"1.0","source":{"id":"2410.24200","kind":"arxiv","version":2}},"canonical_sha256":"052c030316215be206cf93d6bb53b96e7b4e5c670028e1c9bf1cbfdee10476fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"052c030316215be206cf93d6bb53b96e7b4e5c670028e1c9bf1cbfdee10476fe","first_computed_at":"2026-07-05T11:18:40.109970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:40.109970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"udrcbsKPfuDu71a2tF9AZbotlRlmB38qMp+3uzEftljumLR6kwoQJFTN1aBk7Hyz+oCpGuv8jLDIaMwuVlKsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:40.110453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acf0708ad078c3f976c5bab62eb2a4c9e243b5b654352263429528daa39205ef","sha256:ef18106ae6523b748d8455f18399dbaf17d02ee130ac0d89ff70ca4fa2153296"],"state_sha256":"8352016b79c44702e04e5c8900954f4548f8653216e565681aa18148a84fbc4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uz+R+p828sBn0AID3Xh2uyTeRj+td9Hbx6Bbq+liMpIq5ixPWydudYs5kgVw00BVGcDc4OG0Y8E60PG1pjucCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:35:48.800403Z","bundle_sha256":"d39276fcf7259b82e7919a02b53e23e5d0e39a251236eb7a76e80298919da63d"}}