{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GXUPLVY27VNYZDHLTT2VRKF4WC","short_pith_number":"pith:GXUPLVY2","canonical_record":{"source":{"id":"1709.09749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-27T22:05:59Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"5aa066db037da74d472f724cb469d2e88aebe4383f88de71fbe18d1802ba8856","abstract_canon_sha256":"13610c3da5f77e19549177cc17eafff2487da7a50dc7f42812a92ef9ba1b4947"},"schema_version":"1.0"},"canonical_sha256":"35e8f5d71afd5b8c8ceb9cf558a8bcb0a7abfa70b46da8abf8ecc5d9c32eae4f","source":{"kind":"arxiv","id":"1709.09749","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.09749","created_at":"2026-05-18T00:34:06Z"},{"alias_kind":"arxiv_version","alias_value":"1709.09749v1","created_at":"2026-05-18T00:34:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09749","created_at":"2026-05-18T00:34:06Z"},{"alias_kind":"pith_short_12","alias_value":"GXUPLVY27VNY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GXUPLVY27VNYZDHL","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GXUPLVY2","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GXUPLVY27VNYZDHLTT2VRKF4WC","target":"record","payload":{"canonical_record":{"source":{"id":"1709.09749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-27T22:05:59Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"5aa066db037da74d472f724cb469d2e88aebe4383f88de71fbe18d1802ba8856","abstract_canon_sha256":"13610c3da5f77e19549177cc17eafff2487da7a50dc7f42812a92ef9ba1b4947"},"schema_version":"1.0"},"canonical_sha256":"35e8f5d71afd5b8c8ceb9cf558a8bcb0a7abfa70b46da8abf8ecc5d9c32eae4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:06.892510Z","signature_b64":"3TPb8rrlrfxp9Jj2Ion6Coxs5g8WXKFIN9QNiM9ZJ9qQgiU24/XT1lkOrK1r7I2iV3WF1t+Qc6aet6U5NSpoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35e8f5d71afd5b8c8ceb9cf558a8bcb0a7abfa70b46da8abf8ecc5d9c32eae4f","last_reissued_at":"2026-05-18T00:34:06.891819Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:06.891819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.09749","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":"2026-05-18T00:34:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZVjSXpiGR557YwZjX7ugWqh2p7391hjdxDJ5oApBRpT04ObbpQ12n9gk5OjibL8a3gbFW5QMv0uFSXeLfvKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:38:27.846980Z"},"content_sha256":"f16e97f812a005ade8ccd53570150ad12a3f53897927c9bd9e16b8bb579d871d","schema_version":"1.0","event_id":"sha256:f16e97f812a005ade8ccd53570150ad12a3f53897927c9bd9e16b8bb579d871d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GXUPLVY27VNYZDHLTT2VRKF4WC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KeyVec: Key-semantics Preserving Document Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bin Bi, Hao Ma","submitted_at":"2017-09-27T22:05:59Z","abstract_excerpt":"Previous studies have demonstrated the empirical success of word embeddings in various applications. In this paper, we investigate the problem of learning distributed representations for text documents which many machine learning algorithms take as input for a number of NLP tasks.\n  We propose a neural network model, KeyVec, which learns document representations with the goal of preserving key semantics of the input text. It enables the learned low-dimensional vectors to retain the topics and important information from the documents that will flow to downstream tasks. Our empirical evaluations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09749","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":"2026-05-18T00:34:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYEfqCE6bpxwKwyxFM0PGyhHB7K2FWFgznZZS3iosVDAF3PBPLi90hFyA8D1nvVsnnsuF3PaRm6QKoHKxHhpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:38:27.847595Z"},"content_sha256":"b455b6ebbe65a190b246f3e39e5ebeb614612f367fd1db5fe35bec55424d5740","schema_version":"1.0","event_id":"sha256:b455b6ebbe65a190b246f3e39e5ebeb614612f367fd1db5fe35bec55424d5740"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXUPLVY27VNYZDHLTT2VRKF4WC/bundle.json","state_url":"https://pith.science/pith/GXUPLVY27VNYZDHLTT2VRKF4WC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXUPLVY27VNYZDHLTT2VRKF4WC/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":"2026-05-27T21:38:27Z","links":{"resolver":"https://pith.science/pith/GXUPLVY27VNYZDHLTT2VRKF4WC","bundle":"https://pith.science/pith/GXUPLVY27VNYZDHLTT2VRKF4WC/bundle.json","state":"https://pith.science/pith/GXUPLVY27VNYZDHLTT2VRKF4WC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXUPLVY27VNYZDHLTT2VRKF4WC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GXUPLVY27VNYZDHLTT2VRKF4WC","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":"13610c3da5f77e19549177cc17eafff2487da7a50dc7f42812a92ef9ba1b4947","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-27T22:05:59Z","title_canon_sha256":"5aa066db037da74d472f724cb469d2e88aebe4383f88de71fbe18d1802ba8856"},"schema_version":"1.0","source":{"id":"1709.09749","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.09749","created_at":"2026-05-18T00:34:06Z"},{"alias_kind":"arxiv_version","alias_value":"1709.09749v1","created_at":"2026-05-18T00:34:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.09749","created_at":"2026-05-18T00:34:06Z"},{"alias_kind":"pith_short_12","alias_value":"GXUPLVY27VNY","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GXUPLVY27VNYZDHL","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GXUPLVY2","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:b455b6ebbe65a190b246f3e39e5ebeb614612f367fd1db5fe35bec55424d5740","target":"graph","created_at":"2026-05-18T00:34:06Z","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":"Previous studies have demonstrated the empirical success of word embeddings in various applications. In this paper, we investigate the problem of learning distributed representations for text documents which many machine learning algorithms take as input for a number of NLP tasks.\n  We propose a neural network model, KeyVec, which learns document representations with the goal of preserving key semantics of the input text. It enables the learned low-dimensional vectors to retain the topics and important information from the documents that will flow to downstream tasks. Our empirical evaluations","authors_text":"Bin Bi, Hao Ma","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-27T22:05:59Z","title":"KeyVec: Key-semantics Preserving Document Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.09749","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:f16e97f812a005ade8ccd53570150ad12a3f53897927c9bd9e16b8bb579d871d","target":"record","created_at":"2026-05-18T00:34:06Z","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":"13610c3da5f77e19549177cc17eafff2487da7a50dc7f42812a92ef9ba1b4947","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-27T22:05:59Z","title_canon_sha256":"5aa066db037da74d472f724cb469d2e88aebe4383f88de71fbe18d1802ba8856"},"schema_version":"1.0","source":{"id":"1709.09749","kind":"arxiv","version":1}},"canonical_sha256":"35e8f5d71afd5b8c8ceb9cf558a8bcb0a7abfa70b46da8abf8ecc5d9c32eae4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35e8f5d71afd5b8c8ceb9cf558a8bcb0a7abfa70b46da8abf8ecc5d9c32eae4f","first_computed_at":"2026-05-18T00:34:06.891819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:06.891819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3TPb8rrlrfxp9Jj2Ion6Coxs5g8WXKFIN9QNiM9ZJ9qQgiU24/XT1lkOrK1r7I2iV3WF1t+Qc6aet6U5NSpoDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:06.892510Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.09749","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f16e97f812a005ade8ccd53570150ad12a3f53897927c9bd9e16b8bb579d871d","sha256:b455b6ebbe65a190b246f3e39e5ebeb614612f367fd1db5fe35bec55424d5740"],"state_sha256":"cd5d6c16e223e766db91909cf606e04b6e34e85d86fa8ea68ad75dddd1ebc220"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Tdo0t+xyA0Ymk9djlEf1Mq2qUw9EKrLkFxpZgqFg97hgCo4c+EI0oq3OXi5WrXOKwMlX4liJhNb5tRMz4tNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:38:27.851602Z","bundle_sha256":"cc8c06793a9a7d7184a7b02a226f2c9ae21b87863ba977e02cc3f0ec76f720c8"}}