{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WUB5BX7DRHOZEAFPLYELQ2YIZS","short_pith_number":"pith:WUB5BX7D","schema_version":"1.0","canonical_sha256":"b503d0dfe389dd9200af5e08b86b08cc809b357e2224f920c96df711b16645ec","source":{"kind":"arxiv","id":"2305.12517","version":5},"attestation_state":"computed","paper":{"title":"Description-Based Text Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amir DN Cohen, Avshalom Manevich, Shauli Ravfogel, Valentina Pyatkin, Yoav Goldberg","submitted_at":"2023-05-21T17:14:31Z","abstract_excerpt":"Identifying texts with a given semantics is central for many information seeking scenarios. Similarity search over vector embeddings appear to be central to this ability, yet the similarity reflected in current text embeddings is corpus-driven, and is inconsistent and sub-optimal for many use cases. What, then, is a good notion of similarity for effective retrieval of text?\n  We identify the need to search for texts based on abstract descriptions of their content, and the corresponding notion of \\emph{description based similarity}. We demonstrate the inadequacy of current text embeddings and p"},"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":"2305.12517","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-21T17:14:31Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"3d2fb5650bf09fa144dab7baa8d2c806af1a525a10d9c0083132d00b7bfcd8c9","abstract_canon_sha256":"6a8700f13b044f437e5a79fa33c305cea22115582ada2423cec21eeacb060d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:45.877513Z","signature_b64":"3QokISwSwVi+Zw14TqeW68/c/KwXYRxD2uhnn0J6+Cm7za9vGuouh8JFIWLnvABZ+moT+9CD2Ue+GrtER+hYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b503d0dfe389dd9200af5e08b86b08cc809b357e2224f920c96df711b16645ec","last_reissued_at":"2026-07-05T08:47:45.876997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:45.876997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Description-Based Text Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amir DN Cohen, Avshalom Manevich, Shauli Ravfogel, Valentina Pyatkin, Yoav Goldberg","submitted_at":"2023-05-21T17:14:31Z","abstract_excerpt":"Identifying texts with a given semantics is central for many information seeking scenarios. Similarity search over vector embeddings appear to be central to this ability, yet the similarity reflected in current text embeddings is corpus-driven, and is inconsistent and sub-optimal for many use cases. What, then, is a good notion of similarity for effective retrieval of text?\n  We identify the need to search for texts based on abstract descriptions of their content, and the corresponding notion of \\emph{description based similarity}. We demonstrate the inadequacy of current text embeddings and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12517","kind":"arxiv","version":5},"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/2305.12517/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":"2305.12517","created_at":"2026-07-05T08:47:45.877061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12517v5","created_at":"2026-07-05T08:47:45.877061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12517","created_at":"2026-07-05T08:47:45.877061+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUB5BX7DRHOZ","created_at":"2026-07-05T08:47:45.877061+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUB5BX7DRHOZEAFP","created_at":"2026-07-05T08:47:45.877061+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUB5BX7D","created_at":"2026-07-05T08:47:45.877061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06145","citing_title":"Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS","json":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS.json","graph_json":"https://pith.science/api/pith-number/WUB5BX7DRHOZEAFPLYELQ2YIZS/graph.json","events_json":"https://pith.science/api/pith-number/WUB5BX7DRHOZEAFPLYELQ2YIZS/events.json","paper":"https://pith.science/paper/WUB5BX7D"},"agent_actions":{"view_html":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS","download_json":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS.json","view_paper":"https://pith.science/paper/WUB5BX7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12517&json=true","fetch_graph":"https://pith.science/api/pith-number/WUB5BX7DRHOZEAFPLYELQ2YIZS/graph.json","fetch_events":"https://pith.science/api/pith-number/WUB5BX7DRHOZEAFPLYELQ2YIZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS/action/storage_attestation","attest_author":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS/action/author_attestation","sign_citation":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS/action/citation_signature","submit_replication":"https://pith.science/pith/WUB5BX7DRHOZEAFPLYELQ2YIZS/action/replication_record"}},"created_at":"2026-07-05T08:47:45.877061+00:00","updated_at":"2026-07-05T08:47:45.877061+00:00"}