{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SJP5CBTR6DIAAVCIV67M73ULRW","short_pith_number":"pith:SJP5CBTR","canonical_record":{"source":{"id":"1909.13705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-30T13:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"626f74ba4e96e33548e63de38e69c6dad9c4b58b4592703f22480cb55aba196f","abstract_canon_sha256":"0f5b82c3f7f0e43a5ddb399e9cb5dcaf66e49f7042f65a4bc2d91f81a9e9be35"},"schema_version":"1.0"},"canonical_sha256":"925fd10671f0d0005448afbecfee8b8d90edfaf64f78da7224b43f5af67479f3","source":{"kind":"arxiv","id":"1909.13705","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.13705","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"1909.13705v1","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13705","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"SJP5CBTR6DIA","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"SJP5CBTR6DIAAVCI","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"SJP5CBTR","created_at":"2026-07-05T00:08:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SJP5CBTR6DIAAVCIV67M73ULRW","target":"record","payload":{"canonical_record":{"source":{"id":"1909.13705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-30T13:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"626f74ba4e96e33548e63de38e69c6dad9c4b58b4592703f22480cb55aba196f","abstract_canon_sha256":"0f5b82c3f7f0e43a5ddb399e9cb5dcaf66e49f7042f65a4bc2d91f81a9e9be35"},"schema_version":"1.0"},"canonical_sha256":"925fd10671f0d0005448afbecfee8b8d90edfaf64f78da7224b43f5af67479f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:13.044524Z","signature_b64":"/en+GhVw/SySoayUSrmteqSXmL3hoStQkwT8Z0TVuY1ThGgEh+Mk3OfPTU8eem2SPIuie6Ia/r8C/PtA6+uHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925fd10671f0d0005448afbecfee8b8d90edfaf64f78da7224b43f5af67479f3","last_reissued_at":"2026-07-05T00:08:13.044095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:13.044095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.13705","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":"2026-07-05T00:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hoODFUCobIvs64JxSC6ZwDNScXyc4CyALEQjxJTuk1DQvv4we4OND1JlCsEkvrGXALQ7/8Rxn/QBpf/BmkM5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:44:25.969120Z"},"content_sha256":"e9f9ea625b9373097e593966a369a0757d086fbb9dc97ba84395275f56c99c32","schema_version":"1.0","event_id":"sha256:e9f9ea625b9373097e593966a369a0757d086fbb9dc97ba84395275f56c99c32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SJP5CBTR6DIAAVCIV67M73ULRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Closer Look at Data Bias in Neural Extractive Summarization Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danqing Wang, Ming Zhong, Pengfei Liu, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-09-30T13:55:10Z","abstract_excerpt":"In this paper, we take stock of the current state of summarization datasets and explore how different factors of datasets influence the generalization behaviour of neural extractive summarization models. Specifically, we first propose several properties of datasets, which matter for the generalization of summarization models. Then we build the connection between priors residing in datasets and model designs, analyzing how different properties of datasets influence the choices of model structure design and training methods. Finally, by taking a typical dataset as an example, we rethink the proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13705","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.13705/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T8ytBHX40FZGybtEuGFnmPFUj4+Dqc/AzO4obS9CMQIk4dlC42FHoGXPSYvJLFKsxGTb613FxRmlHkTV+g5aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:44:25.970095Z"},"content_sha256":"98ff4ebe2dc56b2928793ce3cc4bdfe7d128947c011c842edc87231894bbf8e3","schema_version":"1.0","event_id":"sha256:98ff4ebe2dc56b2928793ce3cc4bdfe7d128947c011c842edc87231894bbf8e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJP5CBTR6DIAAVCIV67M73ULRW/bundle.json","state_url":"https://pith.science/pith/SJP5CBTR6DIAAVCIV67M73ULRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJP5CBTR6DIAAVCIV67M73ULRW/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":"2026-08-05T19:44:25Z","links":{"resolver":"https://pith.science/pith/SJP5CBTR6DIAAVCIV67M73ULRW","bundle":"https://pith.science/pith/SJP5CBTR6DIAAVCIV67M73ULRW/bundle.json","state":"https://pith.science/pith/SJP5CBTR6DIAAVCIV67M73ULRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJP5CBTR6DIAAVCIV67M73ULRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SJP5CBTR6DIAAVCIV67M73ULRW","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":"0f5b82c3f7f0e43a5ddb399e9cb5dcaf66e49f7042f65a4bc2d91f81a9e9be35","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-30T13:55:10Z","title_canon_sha256":"626f74ba4e96e33548e63de38e69c6dad9c4b58b4592703f22480cb55aba196f"},"schema_version":"1.0","source":{"id":"1909.13705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.13705","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"1909.13705v1","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13705","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"SJP5CBTR6DIA","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"SJP5CBTR6DIAAVCI","created_at":"2026-07-05T00:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"SJP5CBTR","created_at":"2026-07-05T00:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:98ff4ebe2dc56b2928793ce3cc4bdfe7d128947c011c842edc87231894bbf8e3","target":"graph","created_at":"2026-07-05T00:08:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.13705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we take stock of the current state of summarization datasets and explore how different factors of datasets influence the generalization behaviour of neural extractive summarization models. Specifically, we first propose several properties of datasets, which matter for the generalization of summarization models. Then we build the connection between priors residing in datasets and model designs, analyzing how different properties of datasets influence the choices of model structure design and training methods. Finally, by taking a typical dataset as an example, we rethink the proc","authors_text":"Danqing Wang, Ming Zhong, Pengfei Liu, Xipeng Qiu, Xuanjing Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-30T13:55:10Z","title":"A Closer Look at Data Bias in Neural Extractive Summarization Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13705","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:e9f9ea625b9373097e593966a369a0757d086fbb9dc97ba84395275f56c99c32","target":"record","created_at":"2026-07-05T00:08:13Z","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":"0f5b82c3f7f0e43a5ddb399e9cb5dcaf66e49f7042f65a4bc2d91f81a9e9be35","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-30T13:55:10Z","title_canon_sha256":"626f74ba4e96e33548e63de38e69c6dad9c4b58b4592703f22480cb55aba196f"},"schema_version":"1.0","source":{"id":"1909.13705","kind":"arxiv","version":1}},"canonical_sha256":"925fd10671f0d0005448afbecfee8b8d90edfaf64f78da7224b43f5af67479f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"925fd10671f0d0005448afbecfee8b8d90edfaf64f78da7224b43f5af67479f3","first_computed_at":"2026-07-05T00:08:13.044095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:08:13.044095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/en+GhVw/SySoayUSrmteqSXmL3hoStQkwT8Z0TVuY1ThGgEh+Mk3OfPTU8eem2SPIuie6Ia/r8C/PtA6+uHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:08:13.044524Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.13705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9f9ea625b9373097e593966a369a0757d086fbb9dc97ba84395275f56c99c32","sha256:98ff4ebe2dc56b2928793ce3cc4bdfe7d128947c011c842edc87231894bbf8e3"],"state_sha256":"2d9b951fc5f2eede8eb51e70fe795100a730e39a246277f639c5a20335865bd1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xbu0dIn/NtSnAs6GzzkMjxhhr/Pd2oy0epclpvgsgBd7267yw+CGMf2m1NDTkq0djtTEPXaaKmz81XgYnX2rCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:44:25.976694Z","bundle_sha256":"b905dc689354810db7c83774ef71bdfd3499857f71341faff1cc345c81212c46"}}