{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G76DDIHZJOTKRRFXEQ4XSBLFBL","short_pith_number":"pith:G76DDIHZ","canonical_record":{"source":{"id":"2107.05151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-11T23:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"7701cf2c91a5ab619f5d4144b9c59ae8d45c3692cba84f124f26bc07974ca1ec","abstract_canon_sha256":"4780b9a13bdf3e8b2ee602eae864e91d474581bd6a6a31db4070b37ad722e617"},"schema_version":"1.0"},"canonical_sha256":"37fc31a0f94ba6a8c4b724397905650aec4201689fbd51bc0ddc9a00f963752f","source":{"kind":"arxiv","id":"2107.05151","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05151","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05151v1","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05151","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"pith_short_12","alias_value":"G76DDIHZJOTK","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"pith_short_16","alias_value":"G76DDIHZJOTKRRFX","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"pith_short_8","alias_value":"G76DDIHZ","created_at":"2026-07-05T02:57:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G76DDIHZJOTKRRFXEQ4XSBLFBL","target":"record","payload":{"canonical_record":{"source":{"id":"2107.05151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-11T23:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"7701cf2c91a5ab619f5d4144b9c59ae8d45c3692cba84f124f26bc07974ca1ec","abstract_canon_sha256":"4780b9a13bdf3e8b2ee602eae864e91d474581bd6a6a31db4070b37ad722e617"},"schema_version":"1.0"},"canonical_sha256":"37fc31a0f94ba6a8c4b724397905650aec4201689fbd51bc0ddc9a00f963752f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:00.077855Z","signature_b64":"ddlnvD47Tw7HGyWMFr1CQI58Hb7Ro6ljuyq7F6KjI2g2Blf2GHe3fX6nMJQuEjMiSsNLJ7yjDgpmtBlKMlYuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37fc31a0f94ba6a8c4b724397905650aec4201689fbd51bc0ddc9a00f963752f","last_reissued_at":"2026-07-05T02:57:00.077355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:00.077355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.05151","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":"2026-07-05T02:57:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TL+TaziB3Qh23hjGA7UxN6wzrmYH8MHTGIekj0zzsI6ra82b3Z6h4Zheg0nCZRluYQjQzi1GDZCpCqKuqIsKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:34:47.395509Z"},"content_sha256":"3c6ae7e4af550c1e0d70537a462bf2992a10c565c04e8cf228d99648fe1f07e8","schema_version":"1.0","event_id":"sha256:3c6ae7e4af550c1e0d70537a462bf2992a10c565c04e8cf228d99648fe1f07e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G76DDIHZJOTKRRFXEQ4XSBLFBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Document Embedding for Scientific Articles: Efficacy of Word Embeddings vs TFIDF","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"H.J. Meijer, J. Truong, R. Karimi","submitted_at":"2021-07-11T23:58:39Z","abstract_excerpt":"Over the last few years, neural network derived word embeddings became popular in the natural language processing literature. Studies conducted have mostly focused on the quality and application of word embeddings trained on public available corpuses such as Wikipedia or other news and social media sources. However, these studies are limited to generic text and thus lack technical and scientific nuances such as domain specific vocabulary, abbreviations, or scientific formulas which are commonly used in academic context. This research focuses on the performance of word embeddings applied to a l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05151","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/2107.05151/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":"2026-07-05T02:57:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MXRe/ubkxbuDgWWkU+DSvDQvHRc/26wTn1sgCAqCK9IqioIma1rAGty4V9d2p+YhrfZop/iqL6o0SK/MNoFkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:34:47.396016Z"},"content_sha256":"db1b521c3f3d468c3649a59e692997960b3f00dc4a763639df830dc28ff26610","schema_version":"1.0","event_id":"sha256:db1b521c3f3d468c3649a59e692997960b3f00dc4a763639df830dc28ff26610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL/bundle.json","state_url":"https://pith.science/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL/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":"2026-08-09T16:34:47Z","links":{"resolver":"https://pith.science/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL","bundle":"https://pith.science/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL/bundle.json","state":"https://pith.science/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G76DDIHZJOTKRRFXEQ4XSBLFBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G76DDIHZJOTKRRFXEQ4XSBLFBL","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":"4780b9a13bdf3e8b2ee602eae864e91d474581bd6a6a31db4070b37ad722e617","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-11T23:58:39Z","title_canon_sha256":"7701cf2c91a5ab619f5d4144b9c59ae8d45c3692cba84f124f26bc07974ca1ec"},"schema_version":"1.0","source":{"id":"2107.05151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05151","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05151v1","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05151","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"pith_short_12","alias_value":"G76DDIHZJOTK","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"pith_short_16","alias_value":"G76DDIHZJOTKRRFX","created_at":"2026-07-05T02:57:00Z"},{"alias_kind":"pith_short_8","alias_value":"G76DDIHZ","created_at":"2026-07-05T02:57:00Z"}],"graph_snapshots":[{"event_id":"sha256:db1b521c3f3d468c3649a59e692997960b3f00dc4a763639df830dc28ff26610","target":"graph","created_at":"2026-07-05T02:57:00Z","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/2107.05151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over the last few years, neural network derived word embeddings became popular in the natural language processing literature. Studies conducted have mostly focused on the quality and application of word embeddings trained on public available corpuses such as Wikipedia or other news and social media sources. However, these studies are limited to generic text and thus lack technical and scientific nuances such as domain specific vocabulary, abbreviations, or scientific formulas which are commonly used in academic context. This research focuses on the performance of word embeddings applied to a l","authors_text":"H.J. Meijer, J. Truong, R. Karimi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-11T23:58:39Z","title":"Document Embedding for Scientific Articles: Efficacy of Word Embeddings vs TFIDF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05151","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":"sha256:3c6ae7e4af550c1e0d70537a462bf2992a10c565c04e8cf228d99648fe1f07e8","target":"record","created_at":"2026-07-05T02:57:00Z","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":"4780b9a13bdf3e8b2ee602eae864e91d474581bd6a6a31db4070b37ad722e617","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-07-11T23:58:39Z","title_canon_sha256":"7701cf2c91a5ab619f5d4144b9c59ae8d45c3692cba84f124f26bc07974ca1ec"},"schema_version":"1.0","source":{"id":"2107.05151","kind":"arxiv","version":1}},"canonical_sha256":"37fc31a0f94ba6a8c4b724397905650aec4201689fbd51bc0ddc9a00f963752f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37fc31a0f94ba6a8c4b724397905650aec4201689fbd51bc0ddc9a00f963752f","first_computed_at":"2026-07-05T02:57:00.077355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:00.077355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ddlnvD47Tw7HGyWMFr1CQI58Hb7Ro6ljuyq7F6KjI2g2Blf2GHe3fX6nMJQuEjMiSsNLJ7yjDgpmtBlKMlYuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:00.077855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.05151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c6ae7e4af550c1e0d70537a462bf2992a10c565c04e8cf228d99648fe1f07e8","sha256:db1b521c3f3d468c3649a59e692997960b3f00dc4a763639df830dc28ff26610"],"state_sha256":"3b196514ac5ad0d2b60613aafa3e2d7ac9b27bf60e2673567a6e8d7e80ea372e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G/b7Q3/lCSBse0lhC4K1rrAS6r5J/uIir8Rcdq6/5Hdy6Rg3Xgon8OBEgmBF1d4d/nWB2bb0VkbPIZy2LZLBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:34:47.401390Z","bundle_sha256":"e9e784315979a5f4a9f7a51298bf02e7bedfeb3987064d6d52e99e759bc1494c"}}