{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TYSSVHBR5K4H66BY725INU7FOB","short_pith_number":"pith:TYSSVHBR","schema_version":"1.0","canonical_sha256":"9e252a9c31eab87f7838feba86d3e57078ece66cc44d5cadb793d926e6e3950c","source":{"kind":"arxiv","id":"2605.29751","version":1},"attestation_state":"computed","paper":{"title":"DySem: Uncovering Dynamic Semantic Components via Multilingual Consensus for Calculating Semantic Textual Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Huang, Kaijie Zheng, Weiqin Wang, Yile Wang","submitted_at":"2026-05-28T10:47:32Z","abstract_excerpt":"Calculating semantic textual similarity is a foundational task in natural language processing. Current large language models (LLMs) based methods typically rely on extracting last-layer hidden states with fixed dimensions to compute similarity for every text pairs. We argue that this paradigm is suffer from two limitations: (i) The last hidden layer encodes more general knowledge rather than just semantic knowledge, making it suboptimal for semantic similarity computation; (ii) The hidden layer dimensions of LLMs are generally very large, which introduces some redundancy and noise for represen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.29751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T10:47:32Z","cross_cats_sorted":[],"title_canon_sha256":"a92230c62ee721836d9cc54ecb03d8e5fc910970ac75e5032a6586a294242157","abstract_canon_sha256":"bbc42e9553b3917fa170741cd3aa4a40f2d7f7f6dc40df34cec8c7fdacc6e868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:57.818641Z","signature_b64":"OUU/MyOlC+k+BKWDuxGoIlVZwtIKbP+PZQivb/lsr/u461jUo4cC7xngbd1Avpugso6RFDYeqjdTuPAqxjwrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e252a9c31eab87f7838feba86d3e57078ece66cc44d5cadb793d926e6e3950c","last_reissued_at":"2026-05-29T01:05:57.818203Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:57.818203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DySem: Uncovering Dynamic Semantic Components via Multilingual Consensus for Calculating Semantic Textual Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Huang, Kaijie Zheng, Weiqin Wang, Yile Wang","submitted_at":"2026-05-28T10:47:32Z","abstract_excerpt":"Calculating semantic textual similarity is a foundational task in natural language processing. Current large language models (LLMs) based methods typically rely on extracting last-layer hidden states with fixed dimensions to compute similarity for every text pairs. We argue that this paradigm is suffer from two limitations: (i) The last hidden layer encodes more general knowledge rather than just semantic knowledge, making it suboptimal for semantic similarity computation; (ii) The hidden layer dimensions of LLMs are generally very large, which introduces some redundancy and noise for represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29751","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/2605.29751/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.29751","created_at":"2026-05-29T01:05:57.818264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29751v1","created_at":"2026-05-29T01:05:57.818264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29751","created_at":"2026-05-29T01:05:57.818264+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYSSVHBR5K4H","created_at":"2026-05-29T01:05:57.818264+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYSSVHBR5K4H66BY","created_at":"2026-05-29T01:05:57.818264+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYSSVHBR","created_at":"2026-05-29T01:05:57.818264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB","json":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB.json","graph_json":"https://pith.science/api/pith-number/TYSSVHBR5K4H66BY725INU7FOB/graph.json","events_json":"https://pith.science/api/pith-number/TYSSVHBR5K4H66BY725INU7FOB/events.json","paper":"https://pith.science/paper/TYSSVHBR"},"agent_actions":{"view_html":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB","download_json":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB.json","view_paper":"https://pith.science/paper/TYSSVHBR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29751&json=true","fetch_graph":"https://pith.science/api/pith-number/TYSSVHBR5K4H66BY725INU7FOB/graph.json","fetch_events":"https://pith.science/api/pith-number/TYSSVHBR5K4H66BY725INU7FOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB/action/storage_attestation","attest_author":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB/action/author_attestation","sign_citation":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB/action/citation_signature","submit_replication":"https://pith.science/pith/TYSSVHBR5K4H66BY725INU7FOB/action/replication_record"}},"created_at":"2026-05-29T01:05:57.818264+00:00","updated_at":"2026-05-29T01:05:57.818264+00:00"}