{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:TYDCEVWOQDBK55QCE4FYWJNWIY","short_pith_number":"pith:TYDCEVWO","canonical_record":{"source":{"id":"1506.01057","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T20:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"efa46d82f3aad2983c4a8281279c71f6d27ed34d3e8469cd69a638651273eaef","abstract_canon_sha256":"3ad79e283f23eef1517d3309af1c2bfa152d212a435657477c6888678891a27e"},"schema_version":"1.0"},"canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","source":{"kind":"arxiv","id":"1506.01057","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.01057","created_at":"2026-05-18T01:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"1506.01057v2","created_at":"2026-05-18T01:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01057","created_at":"2026-05-18T01:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"TYDCEVWOQDBK","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"TYDCEVWOQDBK55QC","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"TYDCEVWO","created_at":"2026-05-18T12:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:TYDCEVWOQDBK55QCE4FYWJNWIY","target":"record","payload":{"canonical_record":{"source":{"id":"1506.01057","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T20:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"efa46d82f3aad2983c4a8281279c71f6d27ed34d3e8469cd69a638651273eaef","abstract_canon_sha256":"3ad79e283f23eef1517d3309af1c2bfa152d212a435657477c6888678891a27e"},"schema_version":"1.0"},"canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:52.291149Z","signature_b64":"kh/8SbjxL/c1CeOCr7MmSn3R8IR0cNcqtdfFRcuullyCKctu5WKb2fnM6lJdExeyD36aM0tQVoEUBwI9lwd0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","last_reissued_at":"2026-05-18T01:55:52.290731Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:52.290731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.01057","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:55:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQOKc9vpH3Fg/593Zb7X7C2mucfDLDJgApd2f/WQqsI47zgb/nugAtq2fXxS51ZJdm1iR+4OYn+60Jl7S/vaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:10:21.274960Z"},"content_sha256":"541a0da1d7e7721caefa8b628a09fb3f5f5c3e04f5a71e11a98a4e226924cfab","schema_version":"1.0","event_id":"sha256:541a0da1d7e7721caefa8b628a09fb3f5f5c3e04f5a71e11a98a4e226924cfab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:TYDCEVWOQDBK55QCE4FYWJNWIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Hierarchical Neural Autoencoder for Paragraphs and Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Jiwei Li, Minh-Thang Luong","submitted_at":"2015-06-02T20:53:53Z","abstract_excerpt":"Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Long-short term memory) auto-encoder to preserve and reconstruct multi-sentence paragraphs. We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. We evaluate the reconstructed paragraph using standard metrics like ROUGE and Entit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01057","kind":"arxiv","version":2},"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":"2026-05-18T01:55:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SCAAKJzsRQyGgjaYRx7zp/GNGyJIfEbso0hFKSd8e33T1hnavj57dPVV0cCDTdy2yTNhgzjaT1vBceTLCj9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:10:21.275308Z"},"content_sha256":"10464a7eaefec5b2dda14857c5083adeffca3bf102c08d021e196cb147a610f1","schema_version":"1.0","event_id":"sha256:10464a7eaefec5b2dda14857c5083adeffca3bf102c08d021e196cb147a610f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/bundle.json","state_url":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/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":"2026-06-04T20:10:21Z","links":{"resolver":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY","bundle":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/bundle.json","state":"https://pith.science/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYDCEVWOQDBK55QCE4FYWJNWIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:TYDCEVWOQDBK55QCE4FYWJNWIY","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":"3ad79e283f23eef1517d3309af1c2bfa152d212a435657477c6888678891a27e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T20:53:53Z","title_canon_sha256":"efa46d82f3aad2983c4a8281279c71f6d27ed34d3e8469cd69a638651273eaef"},"schema_version":"1.0","source":{"id":"1506.01057","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.01057","created_at":"2026-05-18T01:55:52Z"},{"alias_kind":"arxiv_version","alias_value":"1506.01057v2","created_at":"2026-05-18T01:55:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.01057","created_at":"2026-05-18T01:55:52Z"},{"alias_kind":"pith_short_12","alias_value":"TYDCEVWOQDBK","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"TYDCEVWOQDBK55QC","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"TYDCEVWO","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:10464a7eaefec5b2dda14857c5083adeffca3bf102c08d021e196cb147a610f1","target":"graph","created_at":"2026-05-18T01:55:52Z","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":"Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Long-short term memory) auto-encoder to preserve and reconstruct multi-sentence paragraphs. We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. We evaluate the reconstructed paragraph using standard metrics like ROUGE and Entit","authors_text":"Dan Jurafsky, Jiwei Li, Minh-Thang Luong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T20:53:53Z","title":"A Hierarchical Neural Autoencoder for Paragraphs and Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.01057","kind":"arxiv","version":2},"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":"sha256:541a0da1d7e7721caefa8b628a09fb3f5f5c3e04f5a71e11a98a4e226924cfab","target":"record","created_at":"2026-05-18T01:55:52Z","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":"3ad79e283f23eef1517d3309af1c2bfa152d212a435657477c6888678891a27e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-02T20:53:53Z","title_canon_sha256":"efa46d82f3aad2983c4a8281279c71f6d27ed34d3e8469cd69a638651273eaef"},"schema_version":"1.0","source":{"id":"1506.01057","kind":"arxiv","version":2}},"canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e062256ce80c2aef602270b8b25b6463537e964e17818516724c82a272923a3","first_computed_at":"2026-05-18T01:55:52.290731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:55:52.290731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kh/8SbjxL/c1CeOCr7MmSn3R8IR0cNcqtdfFRcuullyCKctu5WKb2fnM6lJdExeyD36aM0tQVoEUBwI9lwd0AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:55:52.291149Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.01057","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:541a0da1d7e7721caefa8b628a09fb3f5f5c3e04f5a71e11a98a4e226924cfab","sha256:10464a7eaefec5b2dda14857c5083adeffca3bf102c08d021e196cb147a610f1"],"state_sha256":"18d2ab534d1825856cbe3c496c3dd23440febb4f55ba7d2b7cbd1e844617892d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJzEmv04G5BpbGSHyxiZpTYVvb24L2a58FN6R40Lt2xOuzWJpe7k5vb5bJ/5A6nFwg15gVLQIRigeYTVmIwTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:10:21.277420Z","bundle_sha256":"466488ee57a5d4e11f3e250d9be9dc3854267d389ff5ee321a74b12c4a174f94"}}