{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EBKL72EY5DFJMQK5YW3ZRRFYL3","short_pith_number":"pith:EBKL72EY","canonical_record":{"source":{"id":"2305.07826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-13T02:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"a25f7b3c1c453862a7bc25268bd8248d4bf493bcf3ea47931d58eb802cee4392","abstract_canon_sha256":"336a3c3a710910fcd6937df80885e9dbc5b083950f089c733b917a2dc3b92030"},"schema_version":"1.0"},"canonical_sha256":"2054bfe898e8ca96415dc5b798c4b85ee287d3b1e8ba778ef5649e03dc1091c5","source":{"kind":"arxiv","id":"2305.07826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07826","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07826v1","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07826","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"EBKL72EY5DFJ","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"EBKL72EY5DFJMQK5","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"EBKL72EY","created_at":"2026-07-05T06:09:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EBKL72EY5DFJMQK5YW3ZRRFYL3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.07826","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-13T02:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"a25f7b3c1c453862a7bc25268bd8248d4bf493bcf3ea47931d58eb802cee4392","abstract_canon_sha256":"336a3c3a710910fcd6937df80885e9dbc5b083950f089c733b917a2dc3b92030"},"schema_version":"1.0"},"canonical_sha256":"2054bfe898e8ca96415dc5b798c4b85ee287d3b1e8ba778ef5649e03dc1091c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:54.506581Z","signature_b64":"BIBnLe8a37WOBYgOgRbJntLxRlzvzzCHTrYLVR0dNdh+o6XukyvS3z25mb3pqcDD1bW1gXt859Uikz2cuhTCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2054bfe898e8ca96415dc5b798c4b85ee287d3b1e8ba778ef5649e03dc1091c5","last_reissued_at":"2026-07-05T06:09:54.506186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:54.506186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.07826","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":"2026-07-05T06:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pM+3Pb/DMj1yTvKW/dbO4CY7rB5x01zj5ajziNWfzeW7cbJ8TBGZ1TLFXq/Xf4HBURvJvps2T8OxUl98kgVeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:48:04.009163Z"},"content_sha256":"4514f8b311d353cf5265937d348ad147c8c405de22583d419b20f58fc1e2e072","schema_version":"1.0","event_id":"sha256:4514f8b311d353cf5265937d348ad147c8c405de22583d419b20f58fc1e2e072"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EBKL72EY5DFJMQK5YW3ZRRFYL3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frequency-aware Dimension Selection for Static Word Embedding by Mixed Product Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyun Jiang, Lemao Liu, Lingfeng Shen, Ying Chen","submitted_at":"2023-05-13T02:53:37Z","abstract_excerpt":"Static word embedding is still useful, particularly for context-unavailable tasks, because in the case of no context available, pre-trained language models often perform worse than static word embeddings. Although dimension is a key factor determining the quality of static word embeddings, automatic dimension selection is rarely discussed. In this paper, we investigate the impact of word frequency on the dimension selection, and empirically find that word frequency is so vital that it needs to be taken into account during dimension selection. Based on such an empirical finding, this paper prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07826","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/2305.07826/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":"2026-07-05T06:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sE4Te3U2FIhxPAnTAt6SbUR5zKG07hA3DCKNVhJ/iViP+VHMc/t3YnEHPHMaUz6Dcmm3/BBW+jjuN2gY6Pw3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:48:04.009555Z"},"content_sha256":"9d5bfc6b1d89f7dd3dfebd061f7bcfc85f38acca7222869eb34fb5e922ed477e","schema_version":"1.0","event_id":"sha256:9d5bfc6b1d89f7dd3dfebd061f7bcfc85f38acca7222869eb34fb5e922ed477e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3/bundle.json","state_url":"https://pith.science/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3/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":"2026-07-06T15:48:04Z","links":{"resolver":"https://pith.science/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3","bundle":"https://pith.science/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3/bundle.json","state":"https://pith.science/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBKL72EY5DFJMQK5YW3ZRRFYL3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EBKL72EY5DFJMQK5YW3ZRRFYL3","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":"336a3c3a710910fcd6937df80885e9dbc5b083950f089c733b917a2dc3b92030","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-13T02:53:37Z","title_canon_sha256":"a25f7b3c1c453862a7bc25268bd8248d4bf493bcf3ea47931d58eb802cee4392"},"schema_version":"1.0","source":{"id":"2305.07826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07826","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07826v1","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07826","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"EBKL72EY5DFJ","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"EBKL72EY5DFJMQK5","created_at":"2026-07-05T06:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"EBKL72EY","created_at":"2026-07-05T06:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:9d5bfc6b1d89f7dd3dfebd061f7bcfc85f38acca7222869eb34fb5e922ed477e","target":"graph","created_at":"2026-07-05T06:09:54Z","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/2305.07826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Static word embedding is still useful, particularly for context-unavailable tasks, because in the case of no context available, pre-trained language models often perform worse than static word embeddings. Although dimension is a key factor determining the quality of static word embeddings, automatic dimension selection is rarely discussed. In this paper, we investigate the impact of word frequency on the dimension selection, and empirically find that word frequency is so vital that it needs to be taken into account during dimension selection. Based on such an empirical finding, this paper prop","authors_text":"Haiyun Jiang, Lemao Liu, Lingfeng Shen, Ying Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-13T02:53:37Z","title":"Frequency-aware Dimension Selection for Static Word Embedding by Mixed Product Distance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07826","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":"sha256:4514f8b311d353cf5265937d348ad147c8c405de22583d419b20f58fc1e2e072","target":"record","created_at":"2026-07-05T06:09:54Z","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":"336a3c3a710910fcd6937df80885e9dbc5b083950f089c733b917a2dc3b92030","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-13T02:53:37Z","title_canon_sha256":"a25f7b3c1c453862a7bc25268bd8248d4bf493bcf3ea47931d58eb802cee4392"},"schema_version":"1.0","source":{"id":"2305.07826","kind":"arxiv","version":1}},"canonical_sha256":"2054bfe898e8ca96415dc5b798c4b85ee287d3b1e8ba778ef5649e03dc1091c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2054bfe898e8ca96415dc5b798c4b85ee287d3b1e8ba778ef5649e03dc1091c5","first_computed_at":"2026-07-05T06:09:54.506186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:54.506186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BIBnLe8a37WOBYgOgRbJntLxRlzvzzCHTrYLVR0dNdh+o6XukyvS3z25mb3pqcDD1bW1gXt859Uikz2cuhTCDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:54.506581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4514f8b311d353cf5265937d348ad147c8c405de22583d419b20f58fc1e2e072","sha256:9d5bfc6b1d89f7dd3dfebd061f7bcfc85f38acca7222869eb34fb5e922ed477e"],"state_sha256":"52be9ed478388922d9b2ef38e17b5816ec6499969139e0bb2ed634c31f8c7bc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D3anHbjUSXfYK6N7qlLv/TeoveIEnJhZjIOXYuuZDKxV5yBlzeh0fHqqoIE6VpifXFd9vJIu6fZkihbcKnBKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:48:04.011599Z","bundle_sha256":"96fa3e28ef347ae55224e08ac5e29df9f87667f946447b9a606e0191f294dc3d"}}