{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BLIDOAFR3KTWRCG6CY2G64NVGB","short_pith_number":"pith:BLIDOAFR","canonical_record":{"source":{"id":"2110.06388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T22:42:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f4821dc77a76335932963f6b8222c104f5ad02bfce0d7f64bc7a46e7ed254802","abstract_canon_sha256":"1267d99a92d4dc9d526c80e4c75d4cb320b8814cbf445f0507f4d35136690f7c"},"schema_version":"1.0"},"canonical_sha256":"0ad03700b1daa76888de16346f71b5306668c781ceea4aa762a2a7cb267ef5fd","source":{"kind":"arxiv","id":"2110.06388","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06388","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06388v2","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06388","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"BLIDOAFR3KTW","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"BLIDOAFR3KTWRCG6","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"BLIDOAFR","created_at":"2026-07-05T03:24:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BLIDOAFR3KTWRCG6CY2G64NVGB","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T22:42:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f4821dc77a76335932963f6b8222c104f5ad02bfce0d7f64bc7a46e7ed254802","abstract_canon_sha256":"1267d99a92d4dc9d526c80e4c75d4cb320b8814cbf445f0507f4d35136690f7c"},"schema_version":"1.0"},"canonical_sha256":"0ad03700b1daa76888de16346f71b5306668c781ceea4aa762a2a7cb267ef5fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:13.516013Z","signature_b64":"IHPurY4KNpMLfw3PHgDvILgp/iXZD5k8t7fJBh1aE0kGOV2rlH9yHqt6kic1OxILTLOxvj/ttsxvlZsokglcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad03700b1daa76888de16346f71b5306668c781ceea4aa762a2a7cb267ef5fd","last_reissued_at":"2026-07-05T03:24:13.515496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:13.515496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06388","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AV1wAWXcHANGbretZKKDE8MiJ8NhJfvduen00PMrTDdMKcoHN02NR0nivMJSFcwxm7bJH7ZnMCFCeX3NSv0KDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:01:33.357191Z"},"content_sha256":"aa3eadf7b68ccb16608f062f64200bf2702ee9370c1845607afe1370fde89d73","schema_version":"1.0","event_id":"sha256:aa3eadf7b68ccb16608f062f64200bf2702ee9370c1845607afe1370fde89d73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BLIDOAFR3KTWRCG6CY2G64NVGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Congying Xia, Jian-Guo Zhang, Lifang He, Philip S. Yu, Yao Wan, Ye Liu","submitted_at":"2021-10-12T22:42:31Z","abstract_excerpt":"To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. To mitigate these issues, this paper proposes HETFORMER, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization. Specifically, we model different types of semantic nodes in raw text as a potential heterogeneous graph and directly learn heterogeneous relationships (edges) among nodes by T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06388","kind":"arxiv","version":2},"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/2110.06388/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":"2026-07-05T03:24:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3GEnynMi/NriPhT+4+oWbutufcTnOwy0TUzIZ0bCbTt2aFKQhTwPKSKEGXRQkZnjNGTvA61eLMOg691cruHWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:01:33.357816Z"},"content_sha256":"b4dd8b2e1ddaaebe5153f34630182d40e50880d87acba2690fd3427fdb2783b1","schema_version":"1.0","event_id":"sha256:b4dd8b2e1ddaaebe5153f34630182d40e50880d87acba2690fd3427fdb2783b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLIDOAFR3KTWRCG6CY2G64NVGB/bundle.json","state_url":"https://pith.science/pith/BLIDOAFR3KTWRCG6CY2G64NVGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLIDOAFR3KTWRCG6CY2G64NVGB/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":"2026-08-06T07:01:33Z","links":{"resolver":"https://pith.science/pith/BLIDOAFR3KTWRCG6CY2G64NVGB","bundle":"https://pith.science/pith/BLIDOAFR3KTWRCG6CY2G64NVGB/bundle.json","state":"https://pith.science/pith/BLIDOAFR3KTWRCG6CY2G64NVGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLIDOAFR3KTWRCG6CY2G64NVGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BLIDOAFR3KTWRCG6CY2G64NVGB","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":"1267d99a92d4dc9d526c80e4c75d4cb320b8814cbf445f0507f4d35136690f7c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T22:42:31Z","title_canon_sha256":"f4821dc77a76335932963f6b8222c104f5ad02bfce0d7f64bc7a46e7ed254802"},"schema_version":"1.0","source":{"id":"2110.06388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06388","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06388v2","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06388","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"BLIDOAFR3KTW","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"BLIDOAFR3KTWRCG6","created_at":"2026-07-05T03:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"BLIDOAFR","created_at":"2026-07-05T03:24:13Z"}],"graph_snapshots":[{"event_id":"sha256:b4dd8b2e1ddaaebe5153f34630182d40e50880d87acba2690fd3427fdb2783b1","target":"graph","created_at":"2026-07-05T03:24:13Z","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/2110.06388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. To mitigate these issues, this paper proposes HETFORMER, a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization. Specifically, we model different types of semantic nodes in raw text as a potential heterogeneous graph and directly learn heterogeneous relationships (edges) among nodes by T","authors_text":"Congying Xia, Jian-Guo Zhang, Lifang He, Philip S. Yu, Yao Wan, Ye Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T22:42:31Z","title":"HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06388","kind":"arxiv","version":2},"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:aa3eadf7b68ccb16608f062f64200bf2702ee9370c1845607afe1370fde89d73","target":"record","created_at":"2026-07-05T03:24:13Z","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":"1267d99a92d4dc9d526c80e4c75d4cb320b8814cbf445f0507f4d35136690f7c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-12T22:42:31Z","title_canon_sha256":"f4821dc77a76335932963f6b8222c104f5ad02bfce0d7f64bc7a46e7ed254802"},"schema_version":"1.0","source":{"id":"2110.06388","kind":"arxiv","version":2}},"canonical_sha256":"0ad03700b1daa76888de16346f71b5306668c781ceea4aa762a2a7cb267ef5fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ad03700b1daa76888de16346f71b5306668c781ceea4aa762a2a7cb267ef5fd","first_computed_at":"2026-07-05T03:24:13.515496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:13.515496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IHPurY4KNpMLfw3PHgDvILgp/iXZD5k8t7fJBh1aE0kGOV2rlH9yHqt6kic1OxILTLOxvj/ttsxvlZsokglcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:13.516013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa3eadf7b68ccb16608f062f64200bf2702ee9370c1845607afe1370fde89d73","sha256:b4dd8b2e1ddaaebe5153f34630182d40e50880d87acba2690fd3427fdb2783b1"],"state_sha256":"0380ab0a9ecf7ba9d5f75bea50f1650e5b9442e51dca3d9ff13020843b42136e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQkA5YnkjYwyloCnjMu7ioUkdAK+2z39my0qZebFFOBWaog63Qh8HbilzB0E2rJum3S/OpI5/Hctl8nMRyx8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:01:33.363018Z","bundle_sha256":"b38e53297bf390f8ea2082ee6fa65c28b2e79a176784249c0c8e06ddf1fb3c01"}}