{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IJJKPUD2OZ3ZFNE5IV4FDGICEM","short_pith_number":"pith:IJJKPUD2","canonical_record":{"source":{"id":"2109.08569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T14:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"6861c73fb9a7b64cc6265dd1d773724dc8fc4401007d6b1d8015c11612442a1c","abstract_canon_sha256":"5afac7455b66e8eed846a740f58643202b0007d6b1266c3793122b93ee58c2b9"},"schema_version":"1.0"},"canonical_sha256":"4252a7d07a767792b49d45785199022316511e19a8d4cb2ae39c128081d9b32a","source":{"kind":"arxiv","id":"2109.08569","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08569","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08569v1","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08569","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"pith_short_12","alias_value":"IJJKPUD2OZ3Z","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"pith_short_16","alias_value":"IJJKPUD2OZ3ZFNE5","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"pith_short_8","alias_value":"IJJKPUD2","created_at":"2026-07-05T03:15:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IJJKPUD2OZ3ZFNE5IV4FDGICEM","target":"record","payload":{"canonical_record":{"source":{"id":"2109.08569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T14:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"6861c73fb9a7b64cc6265dd1d773724dc8fc4401007d6b1d8015c11612442a1c","abstract_canon_sha256":"5afac7455b66e8eed846a740f58643202b0007d6b1266c3793122b93ee58c2b9"},"schema_version":"1.0"},"canonical_sha256":"4252a7d07a767792b49d45785199022316511e19a8d4cb2ae39c128081d9b32a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:17.459581Z","signature_b64":"zITLg3ZKNANw0/fyBk1qrnT8QFqvyWa+m3gHtKU3SVRw8eq4rInarOELTxmSlJmw3eZhrSbtyQWoeIxAMW75Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4252a7d07a767792b49d45785199022316511e19a8d4cb2ae39c128081d9b32a","last_reissued_at":"2026-07-05T03:15:17.459240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:17.459240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.08569","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":"2026-07-05T03:15:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mP0tHLxv+hQDX/qAQ0GcYQeeoUbqE5nc0eOWoE3KSo818fxCZKAYptZmazgOKvkCTB8L6MAG6HIMh7tFqeFWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T11:09:39.147074Z"},"content_sha256":"9caf2df48b05e5244d284a5665fe6ef7718822a48563e9806e5b12eeb20931aa","schema_version":"1.0","event_id":"sha256:9caf2df48b05e5244d284a5665fe6ef7718822a48563e9806e5b12eeb20931aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IJJKPUD2OZ3ZFNE5IV4FDGICEM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Magooda, Diane Litman","submitted_at":"2021-09-17T14:31:08Z","abstract_excerpt":"This paper explores three simple data manipulation techniques (synthesis, augmentation, curriculum) for improving abstractive summarization models without the need for any additional data. We introduce a method of data synthesis with paraphrasing, a data augmentation technique with sample mixing, and curriculum learning with two new difficulty metrics based on specificity and abstractiveness. We conduct experiments to show that these three techniques can help improve abstractive summarization across two summarization models and two different small datasets. Furthermore, we show that these tech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08569","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/2109.08569/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":"2026-07-05T03:15:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEhRdZMJGT3+jhzp2w4Bxmr8yDAH0fQBBgzPDPqmgopvB9/wKkm8tW9YUyM/7jkb19lWExIrbkuzfPUumN1HDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T11:09:39.147450Z"},"content_sha256":"18b55d3bc18e219c835f947dd1aa6f6a55e987c530d099203965896b3dd28a55","schema_version":"1.0","event_id":"sha256:18b55d3bc18e219c835f947dd1aa6f6a55e987c530d099203965896b3dd28a55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM/bundle.json","state_url":"https://pith.science/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM/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":"2026-07-17T11:09:39Z","links":{"resolver":"https://pith.science/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM","bundle":"https://pith.science/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM/bundle.json","state":"https://pith.science/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJJKPUD2OZ3ZFNE5IV4FDGICEM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IJJKPUD2OZ3ZFNE5IV4FDGICEM","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":"5afac7455b66e8eed846a740f58643202b0007d6b1266c3793122b93ee58c2b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T14:31:08Z","title_canon_sha256":"6861c73fb9a7b64cc6265dd1d773724dc8fc4401007d6b1d8015c11612442a1c"},"schema_version":"1.0","source":{"id":"2109.08569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08569","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08569v1","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08569","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"pith_short_12","alias_value":"IJJKPUD2OZ3Z","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"pith_short_16","alias_value":"IJJKPUD2OZ3ZFNE5","created_at":"2026-07-05T03:15:17Z"},{"alias_kind":"pith_short_8","alias_value":"IJJKPUD2","created_at":"2026-07-05T03:15:17Z"}],"graph_snapshots":[{"event_id":"sha256:18b55d3bc18e219c835f947dd1aa6f6a55e987c530d099203965896b3dd28a55","target":"graph","created_at":"2026-07-05T03:15:17Z","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/2109.08569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores three simple data manipulation techniques (synthesis, augmentation, curriculum) for improving abstractive summarization models without the need for any additional data. We introduce a method of data synthesis with paraphrasing, a data augmentation technique with sample mixing, and curriculum learning with two new difficulty metrics based on specificity and abstractiveness. We conduct experiments to show that these three techniques can help improve abstractive summarization across two summarization models and two different small datasets. Furthermore, we show that these tech","authors_text":"Ahmed Magooda, Diane Litman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T14:31:08Z","title":"Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08569","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":"sha256:9caf2df48b05e5244d284a5665fe6ef7718822a48563e9806e5b12eeb20931aa","target":"record","created_at":"2026-07-05T03:15:17Z","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":"5afac7455b66e8eed846a740f58643202b0007d6b1266c3793122b93ee58c2b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-17T14:31:08Z","title_canon_sha256":"6861c73fb9a7b64cc6265dd1d773724dc8fc4401007d6b1d8015c11612442a1c"},"schema_version":"1.0","source":{"id":"2109.08569","kind":"arxiv","version":1}},"canonical_sha256":"4252a7d07a767792b49d45785199022316511e19a8d4cb2ae39c128081d9b32a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4252a7d07a767792b49d45785199022316511e19a8d4cb2ae39c128081d9b32a","first_computed_at":"2026-07-05T03:15:17.459240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:17.459240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zITLg3ZKNANw0/fyBk1qrnT8QFqvyWa+m3gHtKU3SVRw8eq4rInarOELTxmSlJmw3eZhrSbtyQWoeIxAMW75Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:17.459581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.08569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9caf2df48b05e5244d284a5665fe6ef7718822a48563e9806e5b12eeb20931aa","sha256:18b55d3bc18e219c835f947dd1aa6f6a55e987c530d099203965896b3dd28a55"],"state_sha256":"36a238fa2085ea4c9973668cd61ed6e8876e96940212cfc43020343382b7ecf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YGkt+iwMu5uhxMQ79Ljixa6XFmWhIzZvhescajZVMdHep34wUoWqeUAK5D9SuJrLn5wfz1givYzBk5HeU/Q/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T11:09:39.149659Z","bundle_sha256":"a9b64679b78c5358167364c0f7314820c17353f135dc44bf72ed96412307fbbd"}}