{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PXUOUUHY6EHJJY725EOEYPWZK3","short_pith_number":"pith:PXUOUUHY","canonical_record":{"source":{"id":"1906.08340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-19T20:29:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b17e760095ac53157a27acbf55d14262a4b38bf20431556911e0e4b950f9d681","abstract_canon_sha256":"c839d264b559348a15d47f0f1bc32fae01a1b9e9e10643b274a7382567f42f7d"},"schema_version":"1.0"},"canonical_sha256":"7de8ea50f8f10e94e3fae91c4c3ed956e9e632ed3fb27d4cd0073ccc730bbae3","source":{"kind":"arxiv","id":"1906.08340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08340","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08340v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08340","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"PXUOUUHY6EHJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PXUOUUHY6EHJJY72","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PXUOUUHY","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PXUOUUHY6EHJJY725EOEYPWZK3","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-19T20:29:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b17e760095ac53157a27acbf55d14262a4b38bf20431556911e0e4b950f9d681","abstract_canon_sha256":"c839d264b559348a15d47f0f1bc32fae01a1b9e9e10643b274a7382567f42f7d"},"schema_version":"1.0"},"canonical_sha256":"7de8ea50f8f10e94e3fae91c4c3ed956e9e632ed3fb27d4cd0073ccc730bbae3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.791240Z","signature_b64":"erR2+TNiI8zDoOA+/6+ji4s1i859sKfjbtt/oWOoSAlGLVZ0kR0m+pxIb1yZ+yYwDfx/ItvOcN93eBrlfU6nCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de8ea50f8f10e94e3fae91c4c3ed956e9e632ed3fb27d4cd0073ccc730bbae3","last_reissued_at":"2026-05-17T23:42:52.790711Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.790711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08340","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yGIL6OuLwTONkf6KSCloJSBpHVQ21obzAhdiIIg5H9C2u89r3ddMi6g0Orv+bvuXOleWUDYrbc6WUA9iOzpHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:20:20.765013Z"},"content_sha256":"e898656672c21b52b5ef69a5e634c6590b3baac20d8afae612e1a8e01bd12e6e","schema_version":"1.0","event_id":"sha256:e898656672c21b52b5ef69a5e634c6590b3baac20d8afae612e1a8e01bd12e6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PXUOUUHY6EHJJY725EOEYPWZK3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Compressed Sentence Representations for On-Device Text Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Dhanasekar Sundararaman, Dinghan Shen, Lawrence Carin, Meng Tang, Pengyu Cheng, Qian Yang, Xinyuan Zhang","submitted_at":"2019-06-19T20:29:31Z","abstract_excerpt":"Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise to a large memory footprint and slow retrieval speed, which hinders their applicability to low-resource (memory and computation) platforms, such as mobile devices. In this paper, we propose four different strategies to transform continuous and generic sentence embeddings into a binarized form, while preserving their rich semantic information. The intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08340","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":"2026-05-17T23:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4MMxqLdUU3FULgY0zWUkFNsbk4SS8ukBal2uyyVOL/F79dsIL9m9alZLHrQKiDNtmai/4+UhBt5R+QolR85CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:20:20.765703Z"},"content_sha256":"e07f5d4bd21032970f81590d5a3ee4d3f44f964a89db270002bf7eb46ae6603c","schema_version":"1.0","event_id":"sha256:e07f5d4bd21032970f81590d5a3ee4d3f44f964a89db270002bf7eb46ae6603c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXUOUUHY6EHJJY725EOEYPWZK3/bundle.json","state_url":"https://pith.science/pith/PXUOUUHY6EHJJY725EOEYPWZK3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXUOUUHY6EHJJY725EOEYPWZK3/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":"2026-05-27T14:20:20Z","links":{"resolver":"https://pith.science/pith/PXUOUUHY6EHJJY725EOEYPWZK3","bundle":"https://pith.science/pith/PXUOUUHY6EHJJY725EOEYPWZK3/bundle.json","state":"https://pith.science/pith/PXUOUUHY6EHJJY725EOEYPWZK3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXUOUUHY6EHJJY725EOEYPWZK3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PXUOUUHY6EHJJY725EOEYPWZK3","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":"c839d264b559348a15d47f0f1bc32fae01a1b9e9e10643b274a7382567f42f7d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-19T20:29:31Z","title_canon_sha256":"b17e760095ac53157a27acbf55d14262a4b38bf20431556911e0e4b950f9d681"},"schema_version":"1.0","source":{"id":"1906.08340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08340","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08340v1","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08340","created_at":"2026-05-17T23:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"PXUOUUHY6EHJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PXUOUUHY6EHJJY72","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PXUOUUHY","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:e07f5d4bd21032970f81590d5a3ee4d3f44f964a89db270002bf7eb46ae6603c","target":"graph","created_at":"2026-05-17T23:42:52Z","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":"Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise to a large memory footprint and slow retrieval speed, which hinders their applicability to low-resource (memory and computation) platforms, such as mobile devices. In this paper, we propose four different strategies to transform continuous and generic sentence embeddings into a binarized form, while preserving their rich semantic information. The intr","authors_text":"Asli Celikyilmaz, Dhanasekar Sundararaman, Dinghan Shen, Lawrence Carin, Meng Tang, Pengyu Cheng, Qian Yang, Xinyuan Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-19T20:29:31Z","title":"Learning Compressed Sentence Representations for On-Device Text Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08340","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:e898656672c21b52b5ef69a5e634c6590b3baac20d8afae612e1a8e01bd12e6e","target":"record","created_at":"2026-05-17T23:42:52Z","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":"c839d264b559348a15d47f0f1bc32fae01a1b9e9e10643b274a7382567f42f7d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-19T20:29:31Z","title_canon_sha256":"b17e760095ac53157a27acbf55d14262a4b38bf20431556911e0e4b950f9d681"},"schema_version":"1.0","source":{"id":"1906.08340","kind":"arxiv","version":1}},"canonical_sha256":"7de8ea50f8f10e94e3fae91c4c3ed956e9e632ed3fb27d4cd0073ccc730bbae3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7de8ea50f8f10e94e3fae91c4c3ed956e9e632ed3fb27d4cd0073ccc730bbae3","first_computed_at":"2026-05-17T23:42:52.790711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:52.790711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erR2+TNiI8zDoOA+/6+ji4s1i859sKfjbtt/oWOoSAlGLVZ0kR0m+pxIb1yZ+yYwDfx/ItvOcN93eBrlfU6nCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:52.791240Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e898656672c21b52b5ef69a5e634c6590b3baac20d8afae612e1a8e01bd12e6e","sha256:e07f5d4bd21032970f81590d5a3ee4d3f44f964a89db270002bf7eb46ae6603c"],"state_sha256":"2542032108221dba272c91867bb61572743a8183ba5b71acaa3b62b47a6399dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Fb0oY5SCz3eA5djDWSF3ISXk+Z8H5+NtCpUZ8tsjzfWueiLpvB8+HqiDtkj84lLCY9c5GAnyPLqIFUGUsO/BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:20:20.769385Z","bundle_sha256":"b2de9bd7e46a854de0f14811468342526c41a131e1264fae1f64f81728eadd7a"}}