{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:56GILPPC2GS7QDAKK2WLEKLSCA","short_pith_number":"pith:56GILPPC","canonical_record":{"source":{"id":"1810.05739","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-12T21:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"b6ac7b5e461ee32dbf57d386274f64d75fda9942e9af5ddb416b29bfea0bc0c8","abstract_canon_sha256":"9542fd65e9b119a978f1559e710e36b1e46003417e2bd651d10c7c2b37ddb129"},"schema_version":"1.0"},"canonical_sha256":"ef8c85bde2d1a5f80c0a56acb22972103fca610c58fa332478825387f8afbeba","source":{"kind":"arxiv","id":"1810.05739","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05739","created_at":"2026-05-17T23:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05739v4","created_at":"2026-05-17T23:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05739","created_at":"2026-05-17T23:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"56GILPPC2GS7","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"56GILPPC2GS7QDAK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"56GILPPC","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:56GILPPC2GS7QDAKK2WLEKLSCA","target":"record","payload":{"canonical_record":{"source":{"id":"1810.05739","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-12T21:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"b6ac7b5e461ee32dbf57d386274f64d75fda9942e9af5ddb416b29bfea0bc0c8","abstract_canon_sha256":"9542fd65e9b119a978f1559e710e36b1e46003417e2bd651d10c7c2b37ddb129"},"schema_version":"1.0"},"canonical_sha256":"ef8c85bde2d1a5f80c0a56acb22972103fca610c58fa332478825387f8afbeba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:20.599507Z","signature_b64":"AGYWM0pedR9nuT+1ttx2DaEwULaS+druuTSHrDSROpMKzffGQJlEtN1WpJ6liI8GfFnVBECR5jQ1zMZH4/ixDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef8c85bde2d1a5f80c0a56acb22972103fca610c58fa332478825387f8afbeba","last_reissued_at":"2026-05-17T23:45:20.598948Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:20.598948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.05739","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z3iTdRVLFEiwyLUce+TZvx/dHloICVCpqn4ifw5phIlUHCAPNwgqH32hDScVYDDFxD0xwrzOUgaDkx0D++P5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:20:57.253555Z"},"content_sha256":"398d51bb12a7644f0e9f094d602e43322c7d52ca156fa05a2d2929d799576a18","schema_version":"1.0","event_id":"sha256:398d51bb12a7644f0e9f094d602e43322c7d52ca156fa05a2d2929d799576a18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:56GILPPC2GS7QDAKK2WLEKLSCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Chu, Peter J. Liu","submitted_at":"2018-10-12T21:24:33Z","abstract_excerpt":"Abstractive summarization has been studied using neural sequence transduction methods with datasets of large, paired document-summary examples. However, such datasets are rare and the models trained from them do not generalize to other domains. Recently, some progress has been made in learning sequence-to-sequence mappings with only unpaired examples. In our work, we consider the setting where there are only documents (product or business reviews) with no summaries provided, and propose an end-to-end, neural model architecture to perform unsupervised abstractive summarization. Our proposed mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05739","kind":"arxiv","version":4},"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":"2026-05-17T23:45:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"co+GN26Vvt7K2VzsskK2GdyL/kj9mmrpoU8TuVJ89lgYIt9ZXUTzxroSmXd9Dnv2G0QORswU8wtlwpp9DdJVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:20:57.253896Z"},"content_sha256":"577f42a129e00e8233323ec0171e21fd8a30068f099e89f07cfe59eb6ab1281d","schema_version":"1.0","event_id":"sha256:577f42a129e00e8233323ec0171e21fd8a30068f099e89f07cfe59eb6ab1281d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/56GILPPC2GS7QDAKK2WLEKLSCA/bundle.json","state_url":"https://pith.science/pith/56GILPPC2GS7QDAKK2WLEKLSCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/56GILPPC2GS7QDAKK2WLEKLSCA/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":"2026-06-05T09:20:57Z","links":{"resolver":"https://pith.science/pith/56GILPPC2GS7QDAKK2WLEKLSCA","bundle":"https://pith.science/pith/56GILPPC2GS7QDAKK2WLEKLSCA/bundle.json","state":"https://pith.science/pith/56GILPPC2GS7QDAKK2WLEKLSCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/56GILPPC2GS7QDAKK2WLEKLSCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:56GILPPC2GS7QDAKK2WLEKLSCA","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":"9542fd65e9b119a978f1559e710e36b1e46003417e2bd651d10c7c2b37ddb129","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-12T21:24:33Z","title_canon_sha256":"b6ac7b5e461ee32dbf57d386274f64d75fda9942e9af5ddb416b29bfea0bc0c8"},"schema_version":"1.0","source":{"id":"1810.05739","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05739","created_at":"2026-05-17T23:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05739v4","created_at":"2026-05-17T23:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05739","created_at":"2026-05-17T23:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"56GILPPC2GS7","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"56GILPPC2GS7QDAK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"56GILPPC","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:577f42a129e00e8233323ec0171e21fd8a30068f099e89f07cfe59eb6ab1281d","target":"graph","created_at":"2026-05-17T23:45:20Z","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":"Abstractive summarization has been studied using neural sequence transduction methods with datasets of large, paired document-summary examples. However, such datasets are rare and the models trained from them do not generalize to other domains. Recently, some progress has been made in learning sequence-to-sequence mappings with only unpaired examples. In our work, we consider the setting where there are only documents (product or business reviews) with no summaries provided, and propose an end-to-end, neural model architecture to perform unsupervised abstractive summarization. Our proposed mod","authors_text":"Eric Chu, Peter J. Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-12T21:24:33Z","title":"MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05739","kind":"arxiv","version":4},"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":"sha256:398d51bb12a7644f0e9f094d602e43322c7d52ca156fa05a2d2929d799576a18","target":"record","created_at":"2026-05-17T23:45:20Z","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":"9542fd65e9b119a978f1559e710e36b1e46003417e2bd651d10c7c2b37ddb129","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-10-12T21:24:33Z","title_canon_sha256":"b6ac7b5e461ee32dbf57d386274f64d75fda9942e9af5ddb416b29bfea0bc0c8"},"schema_version":"1.0","source":{"id":"1810.05739","kind":"arxiv","version":4}},"canonical_sha256":"ef8c85bde2d1a5f80c0a56acb22972103fca610c58fa332478825387f8afbeba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef8c85bde2d1a5f80c0a56acb22972103fca610c58fa332478825387f8afbeba","first_computed_at":"2026-05-17T23:45:20.598948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:20.598948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AGYWM0pedR9nuT+1ttx2DaEwULaS+druuTSHrDSROpMKzffGQJlEtN1WpJ6liI8GfFnVBECR5jQ1zMZH4/ixDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:20.599507Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.05739","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:398d51bb12a7644f0e9f094d602e43322c7d52ca156fa05a2d2929d799576a18","sha256:577f42a129e00e8233323ec0171e21fd8a30068f099e89f07cfe59eb6ab1281d"],"state_sha256":"2594f4e68b74900ec8f35fecd06e1d11595d8ac3af109a914d9f2fee85d16ffd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJkDd9x5vMzJiyY39I4ZJTwl4ENoOXp7fFJl/EySqVdHebYG3KLH+/8I5XZZSUameDIyoPfJ/RdEgeLUmYjICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T09:20:57.255793Z","bundle_sha256":"13f371f4379c6fb8b5777d54f351320f60d4bab6a49ede47088d76ed8421ed67"}}