{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SPPD4FA4SSBLC4VFCA4MUV27O3","short_pith_number":"pith:SPPD4FA4","canonical_record":{"source":{"id":"1902.09875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-26T11:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"7608ca4d59f889342cced818063a9676dc4b48bb2a8cb13f3c9371ae22f1b2cf","abstract_canon_sha256":"2f112795846c3b51d81017a7731ec64b8f8d37ebcb93b7c52b96f3138ec2f4c9"},"schema_version":"1.0"},"canonical_sha256":"93de3e141c9482b172a51038ca575f76d3c031fc1082c5e87eb6ad5aab7c4528","source":{"kind":"arxiv","id":"1902.09875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09875","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09875v1","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09875","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"SPPD4FA4SSBL","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SPPD4FA4SSBLC4VF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SPPD4FA4","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SPPD4FA4SSBLC4VFCA4MUV27O3","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-26T11:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"7608ca4d59f889342cced818063a9676dc4b48bb2a8cb13f3c9371ae22f1b2cf","abstract_canon_sha256":"2f112795846c3b51d81017a7731ec64b8f8d37ebcb93b7c52b96f3138ec2f4c9"},"schema_version":"1.0"},"canonical_sha256":"93de3e141c9482b172a51038ca575f76d3c031fc1082c5e87eb6ad5aab7c4528","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:35.115281Z","signature_b64":"fz9DIKtnXAyddax/3xoIurYlmj2qTJ4Y0K4yH0Cdm6Qd3QY8kUuvnfT2Huw+fvEU/s7/Ogr4dX1ioq9HhQ5YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93de3e141c9482b172a51038ca575f76d3c031fc1082c5e87eb6ad5aab7c4528","last_reissued_at":"2026-05-17T23:52:35.114904Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:35.114904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09875","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":"2026-05-17T23:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P15CoWAQi80xSRh00ikN8MyxYvmcw2SwvvguMSAaeGf0C8XB0vSk95d8Uu2j6CsS2tWPoQLfNyBeP9xyq6umDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:42:36.879541Z"},"content_sha256":"76df99e97815f037bfa68e32b1acfe94684fe5541c3b7cee49d811d511e3cf0a","schema_version":"1.0","event_id":"sha256:76df99e97815f037bfa68e32b1acfe94684fe5541c3b7cee49d811d511e3cf0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SPPD4FA4SSBLC4VFCA4MUV27O3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving a tf-idf weighted document vector embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Craig W. Schmidt","submitted_at":"2019-02-26T11:55:35Z","abstract_excerpt":"We examine a number of methods to compute a dense vector embedding for a document in a corpus, given a set of word vectors such as those from word2vec or GloVe. We describe two methods that can improve upon a simple weighted sum, that are optimal in the sense that they maximizes a particular weighted cosine similarity measure.\n  We consider several weighting functions, including inverse document frequency (idf), smooth inverse frequency (SIF), and the sub-sampling function used in word2vec. We find that idf works best for our applications. We also use common component removal proposed by Arora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09875","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":""},"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":"2026-05-17T23:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2VSsB5LeUQjpw19YkVUl6sL7iwLw5bTHkuAEhhhK0BSGSwlba3yDTF4rsXN05WBIzTki9eZOmZE5tj+bJFfLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:42:36.879889Z"},"content_sha256":"c0d30c12420441182251eca2c392b18a0179c8d3c1c3cf62446daac677b53134","schema_version":"1.0","event_id":"sha256:c0d30c12420441182251eca2c392b18a0179c8d3c1c3cf62446daac677b53134"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPPD4FA4SSBLC4VFCA4MUV27O3/bundle.json","state_url":"https://pith.science/pith/SPPD4FA4SSBLC4VFCA4MUV27O3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPPD4FA4SSBLC4VFCA4MUV27O3/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":"2026-06-03T07:42:36Z","links":{"resolver":"https://pith.science/pith/SPPD4FA4SSBLC4VFCA4MUV27O3","bundle":"https://pith.science/pith/SPPD4FA4SSBLC4VFCA4MUV27O3/bundle.json","state":"https://pith.science/pith/SPPD4FA4SSBLC4VFCA4MUV27O3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPPD4FA4SSBLC4VFCA4MUV27O3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SPPD4FA4SSBLC4VFCA4MUV27O3","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":"2f112795846c3b51d81017a7731ec64b8f8d37ebcb93b7c52b96f3138ec2f4c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-26T11:55:35Z","title_canon_sha256":"7608ca4d59f889342cced818063a9676dc4b48bb2a8cb13f3c9371ae22f1b2cf"},"schema_version":"1.0","source":{"id":"1902.09875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09875","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09875v1","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09875","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"SPPD4FA4SSBL","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SPPD4FA4SSBLC4VF","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SPPD4FA4","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:c0d30c12420441182251eca2c392b18a0179c8d3c1c3cf62446daac677b53134","target":"graph","created_at":"2026-05-17T23:52:35Z","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"},"paper":{"abstract_excerpt":"We examine a number of methods to compute a dense vector embedding for a document in a corpus, given a set of word vectors such as those from word2vec or GloVe. We describe two methods that can improve upon a simple weighted sum, that are optimal in the sense that they maximizes a particular weighted cosine similarity measure.\n  We consider several weighting functions, including inverse document frequency (idf), smooth inverse frequency (SIF), and the sub-sampling function used in word2vec. We find that idf works best for our applications. We also use common component removal proposed by Arora","authors_text":"Craig W. Schmidt","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-26T11:55:35Z","title":"Improving a tf-idf weighted document vector embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09875","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":"sha256:76df99e97815f037bfa68e32b1acfe94684fe5541c3b7cee49d811d511e3cf0a","target":"record","created_at":"2026-05-17T23:52:35Z","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":"2f112795846c3b51d81017a7731ec64b8f8d37ebcb93b7c52b96f3138ec2f4c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-26T11:55:35Z","title_canon_sha256":"7608ca4d59f889342cced818063a9676dc4b48bb2a8cb13f3c9371ae22f1b2cf"},"schema_version":"1.0","source":{"id":"1902.09875","kind":"arxiv","version":1}},"canonical_sha256":"93de3e141c9482b172a51038ca575f76d3c031fc1082c5e87eb6ad5aab7c4528","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93de3e141c9482b172a51038ca575f76d3c031fc1082c5e87eb6ad5aab7c4528","first_computed_at":"2026-05-17T23:52:35.114904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:35.114904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fz9DIKtnXAyddax/3xoIurYlmj2qTJ4Y0K4yH0Cdm6Qd3QY8kUuvnfT2Huw+fvEU/s7/Ogr4dX1ioq9HhQ5YDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:35.115281Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76df99e97815f037bfa68e32b1acfe94684fe5541c3b7cee49d811d511e3cf0a","sha256:c0d30c12420441182251eca2c392b18a0179c8d3c1c3cf62446daac677b53134"],"state_sha256":"5a9082c310813ae48999f4cde15cdf0ea71e3f28a295087701dde3fdc912a11d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RVR7KGkr1RLXbApw3rNyuo264Ab38x9tS01G9EPkwbsykARXfRj0YcCAac0jye2rZXt+uQ8SErwTMCljo0k2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:42:36.881868Z","bundle_sha256":"e0722d0e3b3ef5fe9b504ff9d6230b8ce2ec4d4c136c2b1ee438d75fbb30a485"}}