{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:VT2GMQWQBWXADTBY4WVS6VVJNI","short_pith_number":"pith:VT2GMQWQ","canonical_record":{"source":{"id":"1301.6770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-01-28T21:04:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c21f3a44fbde509dddd0a3efbd9191b5eb1bf1e694583c7ee7ba4b77f0920714","abstract_canon_sha256":"012f4d5c9fec9f2e1bb33e89a48d9c35c36fe5fe11741fb82e25d99c0659884c"},"schema_version":"1.0"},"canonical_sha256":"acf46642d00dae01cc38e5ab2f56a96a014574cb08e6cb41f78534015e41a537","source":{"kind":"arxiv","id":"1301.6770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.6770","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"1301.6770v1","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.6770","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"VT2GMQWQBWXA","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"VT2GMQWQBWXADTBY","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"VT2GMQWQ","created_at":"2026-05-18T12:28:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:VT2GMQWQBWXADTBY4WVS6VVJNI","target":"record","payload":{"canonical_record":{"source":{"id":"1301.6770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-01-28T21:04:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c21f3a44fbde509dddd0a3efbd9191b5eb1bf1e694583c7ee7ba4b77f0920714","abstract_canon_sha256":"012f4d5c9fec9f2e1bb33e89a48d9c35c36fe5fe11741fb82e25d99c0659884c"},"schema_version":"1.0"},"canonical_sha256":"acf46642d00dae01cc38e5ab2f56a96a014574cb08e6cb41f78534015e41a537","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:12.415185Z","signature_b64":"JcR7B/tYpJ6yfcSwibEMWq1EIFeQhJ5ad7wIX4REteAIr1/z2Tv7I3xONpRG9A3C+UdUec5QIAVlEoyUrFPcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf46642d00dae01cc38e5ab2f56a96a014574cb08e6cb41f78534015e41a537","last_reissued_at":"2026-05-18T03:35:12.414177Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:12.414177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.6770","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":"2026-05-18T03:35:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DUY5ZgfmIH/m/o+P2PpTyKT57i/IpyEH96vWTXMV67R1ed8RqqumvZ+m65SwevEiH6idXTQHEzi3k3rLViwYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:12:06.584978Z"},"content_sha256":"ee80cceebb3538335bddfe8074eb65b896ed1ed7ecce76f60f48a0a4b54a9ef6","schema_version":"1.0","event_id":"sha256:ee80cceebb3538335bddfe8074eb65b896ed1ed7ecce76f60f48a0a4b54a9ef6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:VT2GMQWQBWXADTBY4WVS6VVJNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An alternative text representation to TF-IDF and Bag-of-Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Fei Sha, Kilian Q. Weinberger, Minmin Chen, Zhixiang (Eddie) Xu","submitted_at":"2013-01-28T21:04:45Z","abstract_excerpt":"In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polysemy. Especially when labeled data is limited (e.g. in document classification), or the text documents are short (e.g. emails or abstracts), many features are rarely observed within the training corpus. This leads to overfitting and reduced generalization accuracy. In this paper we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.6770","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":"2026-05-18T03:35:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jrO8EyMaeO8eN5j7VsJBggoBt5mvDY5YTw7LuG2IrJO5Du83DBbRFzpgrqkeSbPhgAGx66nBulSL0ZfNgF1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:12:06.585341Z"},"content_sha256":"90de16913ee75d4e16b9d55cf1aba7eea747bd9cd50ef3a528c001e3996ccc27","schema_version":"1.0","event_id":"sha256:90de16913ee75d4e16b9d55cf1aba7eea747bd9cd50ef3a528c001e3996ccc27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VT2GMQWQBWXADTBY4WVS6VVJNI/bundle.json","state_url":"https://pith.science/pith/VT2GMQWQBWXADTBY4WVS6VVJNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VT2GMQWQBWXADTBY4WVS6VVJNI/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":"2026-06-01T20:12:06Z","links":{"resolver":"https://pith.science/pith/VT2GMQWQBWXADTBY4WVS6VVJNI","bundle":"https://pith.science/pith/VT2GMQWQBWXADTBY4WVS6VVJNI/bundle.json","state":"https://pith.science/pith/VT2GMQWQBWXADTBY4WVS6VVJNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VT2GMQWQBWXADTBY4WVS6VVJNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:VT2GMQWQBWXADTBY4WVS6VVJNI","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":"012f4d5c9fec9f2e1bb33e89a48d9c35c36fe5fe11741fb82e25d99c0659884c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-01-28T21:04:45Z","title_canon_sha256":"c21f3a44fbde509dddd0a3efbd9191b5eb1bf1e694583c7ee7ba4b77f0920714"},"schema_version":"1.0","source":{"id":"1301.6770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.6770","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"1301.6770v1","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.6770","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"VT2GMQWQBWXA","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"VT2GMQWQBWXADTBY","created_at":"2026-05-18T12:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"VT2GMQWQ","created_at":"2026-05-18T12:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:90de16913ee75d4e16b9d55cf1aba7eea747bd9cd50ef3a528c001e3996ccc27","target":"graph","created_at":"2026-05-18T03:35:12Z","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":"In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polysemy. Especially when labeled data is limited (e.g. in document classification), or the text documents are short (e.g. emails or abstracts), many features are rarely observed within the training corpus. This leads to overfitting and reduced generalization accuracy. In this paper we","authors_text":"Fei Sha, Kilian Q. Weinberger, Minmin Chen, Zhixiang (Eddie) Xu","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-01-28T21:04:45Z","title":"An alternative text representation to TF-IDF and Bag-of-Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.6770","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:ee80cceebb3538335bddfe8074eb65b896ed1ed7ecce76f60f48a0a4b54a9ef6","target":"record","created_at":"2026-05-18T03:35:12Z","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":"012f4d5c9fec9f2e1bb33e89a48d9c35c36fe5fe11741fb82e25d99c0659884c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-01-28T21:04:45Z","title_canon_sha256":"c21f3a44fbde509dddd0a3efbd9191b5eb1bf1e694583c7ee7ba4b77f0920714"},"schema_version":"1.0","source":{"id":"1301.6770","kind":"arxiv","version":1}},"canonical_sha256":"acf46642d00dae01cc38e5ab2f56a96a014574cb08e6cb41f78534015e41a537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acf46642d00dae01cc38e5ab2f56a96a014574cb08e6cb41f78534015e41a537","first_computed_at":"2026-05-18T03:35:12.414177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:35:12.414177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JcR7B/tYpJ6yfcSwibEMWq1EIFeQhJ5ad7wIX4REteAIr1/z2Tv7I3xONpRG9A3C+UdUec5QIAVlEoyUrFPcBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:35:12.415185Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.6770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee80cceebb3538335bddfe8074eb65b896ed1ed7ecce76f60f48a0a4b54a9ef6","sha256:90de16913ee75d4e16b9d55cf1aba7eea747bd9cd50ef3a528c001e3996ccc27"],"state_sha256":"e2581c3fcb3a1b0484b48aa0d662ffe72b0e3b57ab5448c81e7782563d5a815b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxJBKuJZmR73UdYaj3r/6AG8YgYiSOLps1BLWWXHTePt44crdVCYSbVMyHcv9TXelJcywyGzNWSmZxZoCQafAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:12:06.587238Z","bundle_sha256":"836f296c6070b04274eab49de34506842baca1264c47e3ccd94f8bac64eb2424"}}