{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UEZEDEJJHBWPZ7HRO2D2MFWBMR","short_pith_number":"pith:UEZEDEJJ","canonical_record":{"source":{"id":"1603.07252","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-23T16:05:46Z","cross_cats_sorted":[],"title_canon_sha256":"23ec921db868bac4de9d89ef62ca6d92f02008b049429e4da13583ba48374116","abstract_canon_sha256":"b90617c329232f7d34a83efed8c84f953a6f78f05474c4955ca993cf65272e1a"},"schema_version":"1.0"},"canonical_sha256":"a132419129386cfcfcf17687a616c1644820f64413ca4722e3e5cd98c65916ad","source":{"kind":"arxiv","id":"1603.07252","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.07252","created_at":"2026-05-18T01:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"1603.07252v3","created_at":"2026-05-18T01:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.07252","created_at":"2026-05-18T01:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"UEZEDEJJHBWP","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UEZEDEJJHBWPZ7HR","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UEZEDEJJ","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UEZEDEJJHBWPZ7HRO2D2MFWBMR","target":"record","payload":{"canonical_record":{"source":{"id":"1603.07252","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-23T16:05:46Z","cross_cats_sorted":[],"title_canon_sha256":"23ec921db868bac4de9d89ef62ca6d92f02008b049429e4da13583ba48374116","abstract_canon_sha256":"b90617c329232f7d34a83efed8c84f953a6f78f05474c4955ca993cf65272e1a"},"schema_version":"1.0"},"canonical_sha256":"a132419129386cfcfcf17687a616c1644820f64413ca4722e3e5cd98c65916ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:38.386952Z","signature_b64":"hw4EDAn5y3GhHeW8d4+0EIBqQ4FJQVW3WNmI6mBHkbLbFJQt7/W3mTXWQ74hzuk0GcXNSZ5tpA2u4bMMdl6aCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a132419129386cfcfcf17687a616c1644820f64413ca4722e3e5cd98c65916ad","last_reissued_at":"2026-05-18T01:11:38.386575Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:38.386575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.07252","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JMMra8ZDrKpEf7xG88RrXqebkVAmbYWvwPLnw7Lp2reZal7LdqAyVO7hWcydvDWE2iwaVztSd6BQ+LIGIxY0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:02:15.302443Z"},"content_sha256":"9aaab09859a5251c0438b6572f6e08b8e8497220e7659bca9d646b79f02bbf08","schema_version":"1.0","event_id":"sha256:9aaab09859a5251c0438b6572f6e08b8e8497220e7659bca9d646b79f02bbf08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UEZEDEJJHBWPZ7HRO2D2MFWBMR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Summarization by Extracting Sentences and Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianpeng Cheng, Mirella Lapata","submitted_at":"2016-03-23T16:05:46Z","abstract_excerpt":"Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classes of summarization models which can extract sentences or words. We train our models on large scale corpora containing hundreds of thousands of document-summary pairs. Experimental results on two summari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.07252","kind":"arxiv","version":3},"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":"2026-05-18T01:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WpfkMjXbe4NaJjYWIwayLulaHqGcjhMALqVbmdykZaxRg1JL+eWsJMeno61IdXgGFZMvJaSxJy+VP6w0hjlzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:02:15.302846Z"},"content_sha256":"e8156f6594746564b6fd1679495772b95c634f1c86e1098dd7dd5c37919f8cb0","schema_version":"1.0","event_id":"sha256:e8156f6594746564b6fd1679495772b95c634f1c86e1098dd7dd5c37919f8cb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR/bundle.json","state_url":"https://pith.science/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR/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":"2026-05-25T21:02:15Z","links":{"resolver":"https://pith.science/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR","bundle":"https://pith.science/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR/bundle.json","state":"https://pith.science/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UEZEDEJJHBWPZ7HRO2D2MFWBMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UEZEDEJJHBWPZ7HRO2D2MFWBMR","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":"b90617c329232f7d34a83efed8c84f953a6f78f05474c4955ca993cf65272e1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-23T16:05:46Z","title_canon_sha256":"23ec921db868bac4de9d89ef62ca6d92f02008b049429e4da13583ba48374116"},"schema_version":"1.0","source":{"id":"1603.07252","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.07252","created_at":"2026-05-18T01:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"1603.07252v3","created_at":"2026-05-18T01:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.07252","created_at":"2026-05-18T01:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"UEZEDEJJHBWP","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UEZEDEJJHBWPZ7HR","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UEZEDEJJ","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:e8156f6594746564b6fd1679495772b95c634f1c86e1098dd7dd5c37919f8cb0","target":"graph","created_at":"2026-05-18T01:11:38Z","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":"Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classes of summarization models which can extract sentences or words. We train our models on large scale corpora containing hundreds of thousands of document-summary pairs. Experimental results on two summari","authors_text":"Jianpeng Cheng, Mirella Lapata","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-23T16:05:46Z","title":"Neural Summarization by Extracting Sentences and Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.07252","kind":"arxiv","version":3},"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":"sha256:9aaab09859a5251c0438b6572f6e08b8e8497220e7659bca9d646b79f02bbf08","target":"record","created_at":"2026-05-18T01:11:38Z","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":"b90617c329232f7d34a83efed8c84f953a6f78f05474c4955ca993cf65272e1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-23T16:05:46Z","title_canon_sha256":"23ec921db868bac4de9d89ef62ca6d92f02008b049429e4da13583ba48374116"},"schema_version":"1.0","source":{"id":"1603.07252","kind":"arxiv","version":3}},"canonical_sha256":"a132419129386cfcfcf17687a616c1644820f64413ca4722e3e5cd98c65916ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a132419129386cfcfcf17687a616c1644820f64413ca4722e3e5cd98c65916ad","first_computed_at":"2026-05-18T01:11:38.386575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:38.386575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hw4EDAn5y3GhHeW8d4+0EIBqQ4FJQVW3WNmI6mBHkbLbFJQt7/W3mTXWQ74hzuk0GcXNSZ5tpA2u4bMMdl6aCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:38.386952Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.07252","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9aaab09859a5251c0438b6572f6e08b8e8497220e7659bca9d646b79f02bbf08","sha256:e8156f6594746564b6fd1679495772b95c634f1c86e1098dd7dd5c37919f8cb0"],"state_sha256":"90ac635571aac8485131a0e37794793afc68345d9de910b58b0908f4bd54aa76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R0H9CIRvqfw4VDcWu4kXzgWEjvT+fs8ZUIfGdlwfUyh19zCsfJ+XK0KG5nKVgms9SitWHE9f115tFNWvhu4FDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:02:15.306599Z","bundle_sha256":"7b29c5a33dc5a6ddf03aa30718e2be23f9441bf8da2d60b029a400aff97a595d"}}