{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M2TAOF623IHA2F2PS5NDOCRQDS","short_pith_number":"pith:M2TAOF62","canonical_record":{"source":{"id":"2303.14011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T14:07:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7be143f16c671132658179784a8645a537800a01b71925783f2f5e16e097a24","abstract_canon_sha256":"f4b910fcb6059818a9fc44c395000ba2dcd9bb0a96639112427fcd6a84d82f53"},"schema_version":"1.0"},"canonical_sha256":"66a60717dada0e0d174f975a370a301c9ba6f697bc47f6140074e6acc08cb4fa","source":{"kind":"arxiv","id":"2303.14011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14011","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14011v1","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14011","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"M2TAOF623IHA","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"M2TAOF623IHA2F2P","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"M2TAOF62","created_at":"2026-07-05T05:54:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M2TAOF623IHA2F2PS5NDOCRQDS","target":"record","payload":{"canonical_record":{"source":{"id":"2303.14011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T14:07:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7be143f16c671132658179784a8645a537800a01b71925783f2f5e16e097a24","abstract_canon_sha256":"f4b910fcb6059818a9fc44c395000ba2dcd9bb0a96639112427fcd6a84d82f53"},"schema_version":"1.0"},"canonical_sha256":"66a60717dada0e0d174f975a370a301c9ba6f697bc47f6140074e6acc08cb4fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:22.626545Z","signature_b64":"0Z97wHHWbPwA/pksV4V+Fxwp1rlosVe3j2snJJeflYx+TPqHiGk1WP8TDrHsgwqHmcdtfqZJi6ABfnVWCvjQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66a60717dada0e0d174f975a370a301c9ba6f697bc47f6140074e6acc08cb4fa","last_reissued_at":"2026-07-05T05:54:22.626115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:22.626115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.14011","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":"2026-07-05T05:54:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grQ6OMmMD/GbaogMV6rtpLSikWdGVtaadp7KT8G4B0XFO2GyUbtz0hCWKUTUSMsvxLHsJKbXlyMGtQvI0uh/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:33:59.958918Z"},"content_sha256":"0607dcadbadc10f071c828686f92183f9e347c9423e880eb22197c0d874e4c05","schema_version":"1.0","event_id":"sha256:0607dcadbadc10f071c828686f92183f9e347c9423e880eb22197c0d874e4c05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M2TAOF623IHA2F2PS5NDOCRQDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hong-Han Shuai, Yi-Syuan Chen, Yun-Zhu Song","submitted_at":"2023-03-24T14:07:03Z","abstract_excerpt":"Neural abstractive summarization has been widely studied and achieved great success with large-scale corpora. However, the considerable cost of annotating data motivates the need for learning strategies under low-resource settings. In this paper, we investigate the problems of learning summarizers with only few examples and propose corresponding methods for improvements. First, typical transfer learning methods are prone to be affected by data properties and learning objectives in the pretext tasks. Therefore, based on pretrained language models, we further present a meta learning framework to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14011","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/2303.14011/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":"2026-07-05T05:54:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GzF/rRfamNoLeKVtEsHK4ebcQk3Yhudw+bakxX2EQz2/bBjJDQWNIPM1Wucf1LRPP9vyZYtVIKYJ/iXvahaGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:33:59.959449Z"},"content_sha256":"e83e0cbaafaba9859d9e0a8ed033d818a23bddd7dc4dbed4e96d7ca5c4c6aab4","schema_version":"1.0","event_id":"sha256:e83e0cbaafaba9859d9e0a8ed033d818a23bddd7dc4dbed4e96d7ca5c4c6aab4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2TAOF623IHA2F2PS5NDOCRQDS/bundle.json","state_url":"https://pith.science/pith/M2TAOF623IHA2F2PS5NDOCRQDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2TAOF623IHA2F2PS5NDOCRQDS/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":"2026-08-19T18:33:59Z","links":{"resolver":"https://pith.science/pith/M2TAOF623IHA2F2PS5NDOCRQDS","bundle":"https://pith.science/pith/M2TAOF623IHA2F2PS5NDOCRQDS/bundle.json","state":"https://pith.science/pith/M2TAOF623IHA2F2PS5NDOCRQDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2TAOF623IHA2F2PS5NDOCRQDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M2TAOF623IHA2F2PS5NDOCRQDS","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":"f4b910fcb6059818a9fc44c395000ba2dcd9bb0a96639112427fcd6a84d82f53","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T14:07:03Z","title_canon_sha256":"d7be143f16c671132658179784a8645a537800a01b71925783f2f5e16e097a24"},"schema_version":"1.0","source":{"id":"2303.14011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14011","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14011v1","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14011","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"M2TAOF623IHA","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"M2TAOF623IHA2F2P","created_at":"2026-07-05T05:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"M2TAOF62","created_at":"2026-07-05T05:54:22Z"}],"graph_snapshots":[{"event_id":"sha256:e83e0cbaafaba9859d9e0a8ed033d818a23bddd7dc4dbed4e96d7ca5c4c6aab4","target":"graph","created_at":"2026-07-05T05:54:22Z","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/2303.14011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural abstractive summarization has been widely studied and achieved great success with large-scale corpora. However, the considerable cost of annotating data motivates the need for learning strategies under low-resource settings. In this paper, we investigate the problems of learning summarizers with only few examples and propose corresponding methods for improvements. First, typical transfer learning methods are prone to be affected by data properties and learning objectives in the pretext tasks. Therefore, based on pretrained language models, we further present a meta learning framework to","authors_text":"Hong-Han Shuai, Yi-Syuan Chen, Yun-Zhu Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T14:07:03Z","title":"SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14011","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":"sha256:0607dcadbadc10f071c828686f92183f9e347c9423e880eb22197c0d874e4c05","target":"record","created_at":"2026-07-05T05:54:22Z","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":"f4b910fcb6059818a9fc44c395000ba2dcd9bb0a96639112427fcd6a84d82f53","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T14:07:03Z","title_canon_sha256":"d7be143f16c671132658179784a8645a537800a01b71925783f2f5e16e097a24"},"schema_version":"1.0","source":{"id":"2303.14011","kind":"arxiv","version":1}},"canonical_sha256":"66a60717dada0e0d174f975a370a301c9ba6f697bc47f6140074e6acc08cb4fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66a60717dada0e0d174f975a370a301c9ba6f697bc47f6140074e6acc08cb4fa","first_computed_at":"2026-07-05T05:54:22.626115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:22.626115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Z97wHHWbPwA/pksV4V+Fxwp1rlosVe3j2snJJeflYx+TPqHiGk1WP8TDrHsgwqHmcdtfqZJi6ABfnVWCvjQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:22.626545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0607dcadbadc10f071c828686f92183f9e347c9423e880eb22197c0d874e4c05","sha256:e83e0cbaafaba9859d9e0a8ed033d818a23bddd7dc4dbed4e96d7ca5c4c6aab4"],"state_sha256":"11fe87deb88b2711dda6cd2b21fcb21aac73553b9b3184193a9db48924e941f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqvNk0Y+35FV1wJAgTIsRfheda29SL97wJHOLz4zBtpg+ZpKYg99BqC1Qx8jPmz2s6ORjGyN8qRjXRFA3Oj/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:33:59.963963Z","bundle_sha256":"d6023d1784e28b936fa3e939e14abb4bf504e0daaa83b7402d43df0f4740c341"}}