{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YYSI5RLDD75MSQNZEAAQZB7323","short_pith_number":"pith:YYSI5RLD","canonical_record":{"source":{"id":"2202.09049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T07:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"b4084fbf2b3891e3e04cfc61632fd882c07c1827f871c860c5ba16375ca04e16","abstract_canon_sha256":"45efd9539547a833ff9d5598d9322e98bf5bb07ff1989515db2f1437131c4938"},"schema_version":"1.0"},"canonical_sha256":"c6248ec5631ffac941b920010c87fbd6ca575a6235c0c8f5d3477c6861e08278","source":{"kind":"arxiv","id":"2202.09049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09049","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09049v1","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09049","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"YYSI5RLDD75M","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"YYSI5RLDD75MSQNZ","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"YYSI5RLD","created_at":"2026-07-05T03:58:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YYSI5RLDD75MSQNZEAAQZB7323","target":"record","payload":{"canonical_record":{"source":{"id":"2202.09049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T07:11:04Z","cross_cats_sorted":[],"title_canon_sha256":"b4084fbf2b3891e3e04cfc61632fd882c07c1827f871c860c5ba16375ca04e16","abstract_canon_sha256":"45efd9539547a833ff9d5598d9322e98bf5bb07ff1989515db2f1437131c4938"},"schema_version":"1.0"},"canonical_sha256":"c6248ec5631ffac941b920010c87fbd6ca575a6235c0c8f5d3477c6861e08278","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:09.226443Z","signature_b64":"KT2Mf0oWCYPcO8h97T/yn/F6oBGQX4g0dkbRIkBOn52tC2Pu3BktoqTLn0PvUE8ABpH5zN4VLEJeIAhdjdqWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6248ec5631ffac941b920010c87fbd6ca575a6235c0c8f5d3477c6861e08278","last_reissued_at":"2026-07-05T03:58:09.226040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:09.226040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.09049","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":"2026-07-05T03:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5g2a60J8fZNQW0jNxXrSnWZwkhduhWEO4jEOb75tlatBgJWzbGWWMUwHRcBm52ANhrZo6mISS/3pC0JARAnuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:21:13.047973Z"},"content_sha256":"efbc20a50795018b9c57849d1fa9bb90e8cd01129e09b23a8f883b19a9f08f71","schema_version":"1.0","event_id":"sha256:efbc20a50795018b9c57849d1fa9bb90e8cd01129e09b23a8f883b19a9f08f71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YYSI5RLDD75MSQNZEAAQZB7323","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLSEG: Contrastive Learning of Story Ending Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luxi Xing, Ping Guo, Wei Peng, Yue Hu, Yunpeng Li, Yuqiang Xie","submitted_at":"2022-02-18T07:11:04Z","abstract_excerpt":"Story Ending Generation (SEG) is a challenging task in natural language generation. Recently, methods based on Pre-trained Language Models (PLM) have achieved great prosperity, which can produce fluent and coherent story endings. However, the pre-training objective of PLM-based methods is unable to model the consistency between story context and ending. The goal of this paper is to adopt contrastive learning to generate endings more consistent with story context, while there are two main challenges in contrastive learning of SEG. First is the negative sampling of wrong endings inconsistent wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09049","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/2202.09049/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":"2026-07-05T03:58:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxpJ2F/g2JIvGzVpx9zd2VVthJJAcosyp4bc/sCjWTVpjiq0EKpgCRbzIsj9Y9qWM0ByQwlelshA+VFSPXyjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:21:13.048482Z"},"content_sha256":"4dfc5c08b0b18bebd594afac17288cf37e69d8e86243698941dfe01d3a27f6c5","schema_version":"1.0","event_id":"sha256:4dfc5c08b0b18bebd594afac17288cf37e69d8e86243698941dfe01d3a27f6c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYSI5RLDD75MSQNZEAAQZB7323/bundle.json","state_url":"https://pith.science/pith/YYSI5RLDD75MSQNZEAAQZB7323/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYSI5RLDD75MSQNZEAAQZB7323/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":"2026-08-03T20:21:13Z","links":{"resolver":"https://pith.science/pith/YYSI5RLDD75MSQNZEAAQZB7323","bundle":"https://pith.science/pith/YYSI5RLDD75MSQNZEAAQZB7323/bundle.json","state":"https://pith.science/pith/YYSI5RLDD75MSQNZEAAQZB7323/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYSI5RLDD75MSQNZEAAQZB7323/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YYSI5RLDD75MSQNZEAAQZB7323","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":"45efd9539547a833ff9d5598d9322e98bf5bb07ff1989515db2f1437131c4938","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T07:11:04Z","title_canon_sha256":"b4084fbf2b3891e3e04cfc61632fd882c07c1827f871c860c5ba16375ca04e16"},"schema_version":"1.0","source":{"id":"2202.09049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.09049","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2202.09049v1","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09049","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"YYSI5RLDD75M","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"YYSI5RLDD75MSQNZ","created_at":"2026-07-05T03:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"YYSI5RLD","created_at":"2026-07-05T03:58:09Z"}],"graph_snapshots":[{"event_id":"sha256:4dfc5c08b0b18bebd594afac17288cf37e69d8e86243698941dfe01d3a27f6c5","target":"graph","created_at":"2026-07-05T03:58:09Z","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/2202.09049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Story Ending Generation (SEG) is a challenging task in natural language generation. Recently, methods based on Pre-trained Language Models (PLM) have achieved great prosperity, which can produce fluent and coherent story endings. However, the pre-training objective of PLM-based methods is unable to model the consistency between story context and ending. The goal of this paper is to adopt contrastive learning to generate endings more consistent with story context, while there are two main challenges in contrastive learning of SEG. First is the negative sampling of wrong endings inconsistent wit","authors_text":"Luxi Xing, Ping Guo, Wei Peng, Yue Hu, Yunpeng Li, Yuqiang Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T07:11:04Z","title":"CLSEG: Contrastive Learning of Story Ending Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09049","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:efbc20a50795018b9c57849d1fa9bb90e8cd01129e09b23a8f883b19a9f08f71","target":"record","created_at":"2026-07-05T03:58:09Z","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":"45efd9539547a833ff9d5598d9322e98bf5bb07ff1989515db2f1437131c4938","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-18T07:11:04Z","title_canon_sha256":"b4084fbf2b3891e3e04cfc61632fd882c07c1827f871c860c5ba16375ca04e16"},"schema_version":"1.0","source":{"id":"2202.09049","kind":"arxiv","version":1}},"canonical_sha256":"c6248ec5631ffac941b920010c87fbd6ca575a6235c0c8f5d3477c6861e08278","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6248ec5631ffac941b920010c87fbd6ca575a6235c0c8f5d3477c6861e08278","first_computed_at":"2026-07-05T03:58:09.226040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:09.226040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KT2Mf0oWCYPcO8h97T/yn/F6oBGQX4g0dkbRIkBOn52tC2Pu3BktoqTLn0PvUE8ABpH5zN4VLEJeIAhdjdqWBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:09.226443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.09049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efbc20a50795018b9c57849d1fa9bb90e8cd01129e09b23a8f883b19a9f08f71","sha256:4dfc5c08b0b18bebd594afac17288cf37e69d8e86243698941dfe01d3a27f6c5"],"state_sha256":"3a9080fd44dd39bd119aa7c3bcec5572dd5893144dce20834f6b57d505d2ef51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ONgb0AmDxEjBGwLTTrxidgaK401jHH89BV0mgkoWEj3pPX6hNOuF5FRp9C8vdWp4mIQ1tJc0BIT8fr8MnxXBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:21:13.053435Z","bundle_sha256":"7e9434e2c1c2fec5d205cc488dba0fc927a4e3c496b422153b242a798586a6ac"}}