{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:75CEOYP7RLRIRT2P34MVFUJDUL","short_pith_number":"pith:75CEOYP7","canonical_record":{"source":{"id":"1808.01160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-03T11:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"a9663de69f7e50346a93ba80e265d701623f457bfd8ca44554c1e931e6c3b4c7","abstract_canon_sha256":"04e142a44d33276675e4034b31a85a3cee6df725074ea7368b56d77cd4817d92"},"schema_version":"1.0"},"canonical_sha256":"ff444761ff8ae288cf4fdf1952d123a2dc091c2de440d8fb22bc721549428ecf","source":{"kind":"arxiv","id":"1808.01160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.01160","created_at":"2026-05-18T00:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"1808.01160v1","created_at":"2026-05-18T00:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01160","created_at":"2026-05-18T00:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"75CEOYP7RLRI","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"75CEOYP7RLRIRT2P","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"75CEOYP7","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:75CEOYP7RLRIRT2P34MVFUJDUL","target":"record","payload":{"canonical_record":{"source":{"id":"1808.01160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-03T11:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"a9663de69f7e50346a93ba80e265d701623f457bfd8ca44554c1e931e6c3b4c7","abstract_canon_sha256":"04e142a44d33276675e4034b31a85a3cee6df725074ea7368b56d77cd4817d92"},"schema_version":"1.0"},"canonical_sha256":"ff444761ff8ae288cf4fdf1952d123a2dc091c2de440d8fb22bc721549428ecf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:58.810713Z","signature_b64":"B3cLgrDKnXcDN4YY286xiOw02vUPeFifqfidQ7ggcKqkYAd7IMp7+vCjasr2MjlDdY7wcJEuxasfmEJ8l9+2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff444761ff8ae288cf4fdf1952d123a2dc091c2de440d8fb22bc721549428ecf","last_reissued_at":"2026-05-18T00:08:58.810205Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:58.810205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.01160","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":"2026-05-18T00:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3uTmCGt0dd7HQagtPti/aLtHMkjU0crkqpfs1JTcIXwstKcQ7/xoFPw5uFOQSrMhkC8FWVI9dcSpLYEpSV9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:24:22.770540Z"},"content_sha256":"1bd7d0170a11cb5fc1626695102209e16a14dc327eec5d5171482efe08a1731a","schema_version":"1.0","event_id":"sha256:1bd7d0170a11cb5fc1626695102209e16a14dc327eec5d5171482efe08a1731a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:75CEOYP7RLRIRT2P34MVFUJDUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Purely Convolutional Text Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian Lancucki, Jan Chorowski, Szymon Malik","submitted_at":"2018-08-03T11:31:26Z","abstract_excerpt":"In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our work derives from a recently proposed recursive convolutional architecture for auto-encoding text paragraphs at byte level. We propose alternations that significantly reduce training time, the number of parameters, and improve auto-encoding accuracy. Finally, we evaluate the representations created by our model on tasks from SentEval benchmark suite, and show that it can serve as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01160","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":"2026-05-18T00:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydSeuAB/UBzMfplAbgybsO2qfUu15oGPgKUKbasfkLCFqWdO0+6g5WUn0sVgzNHOm7OtaLj8TCnrQT/z9fy0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:24:22.771210Z"},"content_sha256":"a3f120b7393c4417f7c5461f295770157df156a97c50e02adc5009a62879bfe6","schema_version":"1.0","event_id":"sha256:a3f120b7393c4417f7c5461f295770157df156a97c50e02adc5009a62879bfe6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75CEOYP7RLRIRT2P34MVFUJDUL/bundle.json","state_url":"https://pith.science/pith/75CEOYP7RLRIRT2P34MVFUJDUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75CEOYP7RLRIRT2P34MVFUJDUL/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":"2026-06-09T05:24:22Z","links":{"resolver":"https://pith.science/pith/75CEOYP7RLRIRT2P34MVFUJDUL","bundle":"https://pith.science/pith/75CEOYP7RLRIRT2P34MVFUJDUL/bundle.json","state":"https://pith.science/pith/75CEOYP7RLRIRT2P34MVFUJDUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75CEOYP7RLRIRT2P34MVFUJDUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:75CEOYP7RLRIRT2P34MVFUJDUL","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":"04e142a44d33276675e4034b31a85a3cee6df725074ea7368b56d77cd4817d92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-03T11:31:26Z","title_canon_sha256":"a9663de69f7e50346a93ba80e265d701623f457bfd8ca44554c1e931e6c3b4c7"},"schema_version":"1.0","source":{"id":"1808.01160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.01160","created_at":"2026-05-18T00:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"1808.01160v1","created_at":"2026-05-18T00:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01160","created_at":"2026-05-18T00:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"75CEOYP7RLRI","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"75CEOYP7RLRIRT2P","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"75CEOYP7","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:a3f120b7393c4417f7c5461f295770157df156a97c50e02adc5009a62879bfe6","target":"graph","created_at":"2026-05-18T00:08:58Z","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 this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our work derives from a recently proposed recursive convolutional architecture for auto-encoding text paragraphs at byte level. We propose alternations that significantly reduce training time, the number of parameters, and improve auto-encoding accuracy. Finally, we evaluate the representations created by our model on tasks from SentEval benchmark suite, and show that it can serve as","authors_text":"Adrian Lancucki, Jan Chorowski, Szymon Malik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-03T11:31:26Z","title":"Efficient Purely Convolutional Text Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01160","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":"sha256:1bd7d0170a11cb5fc1626695102209e16a14dc327eec5d5171482efe08a1731a","target":"record","created_at":"2026-05-18T00:08:58Z","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":"04e142a44d33276675e4034b31a85a3cee6df725074ea7368b56d77cd4817d92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-03T11:31:26Z","title_canon_sha256":"a9663de69f7e50346a93ba80e265d701623f457bfd8ca44554c1e931e6c3b4c7"},"schema_version":"1.0","source":{"id":"1808.01160","kind":"arxiv","version":1}},"canonical_sha256":"ff444761ff8ae288cf4fdf1952d123a2dc091c2de440d8fb22bc721549428ecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff444761ff8ae288cf4fdf1952d123a2dc091c2de440d8fb22bc721549428ecf","first_computed_at":"2026-05-18T00:08:58.810205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:58.810205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B3cLgrDKnXcDN4YY286xiOw02vUPeFifqfidQ7ggcKqkYAd7IMp7+vCjasr2MjlDdY7wcJEuxasfmEJ8l9+2Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:58.810713Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.01160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bd7d0170a11cb5fc1626695102209e16a14dc327eec5d5171482efe08a1731a","sha256:a3f120b7393c4417f7c5461f295770157df156a97c50e02adc5009a62879bfe6"],"state_sha256":"b8f84950f34e6797b10fdc3f3d5f8d55806dc3db13f4eae1ce22a98b63903e4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMleyKfe3vjxKf+wqT10Y6G63LWjsGS7R6Cbf+RZmLMxqok6JVTy4MEK+QX4kTQuWe8WR9BKtQkdoqTx3p0KAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T05:24:22.775090Z","bundle_sha256":"ca992b79973370b1200251ac11efd9f06483d280651d8c22797a25cf8034e267"}}