{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KSCEWT2YDBN6RIR6AMZYLHXLOU","short_pith_number":"pith:KSCEWT2Y","canonical_record":{"source":{"id":"2310.12580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T08:41:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"742f9d871caf58545b4d5138dafd3b511e0856f7b35b42cd16c85a0ba7542717","abstract_canon_sha256":"0bdfa653c9add6d6d7a49e9ef9b2765a26c2bca96989fee6400598364931d9be"},"schema_version":"1.0"},"canonical_sha256":"54844b4f58185be8a23e0333859eeb7512c3a7e0d4bf6680156e3fe0a4aa3a55","source":{"kind":"arxiv","id":"2310.12580","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12580","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12580v2","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12580","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"KSCEWT2YDBN6","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"KSCEWT2YDBN6RIR6","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"KSCEWT2Y","created_at":"2026-07-05T07:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KSCEWT2YDBN6RIR6AMZYLHXLOU","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T08:41:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"742f9d871caf58545b4d5138dafd3b511e0856f7b35b42cd16c85a0ba7542717","abstract_canon_sha256":"0bdfa653c9add6d6d7a49e9ef9b2765a26c2bca96989fee6400598364931d9be"},"schema_version":"1.0"},"canonical_sha256":"54844b4f58185be8a23e0333859eeb7512c3a7e0d4bf6680156e3fe0a4aa3a55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:32.755526Z","signature_b64":"xNSnFyK8MkbRdCBo2Sim0mAP06AF/3f97yWPUtJLseN//sWfxZMxbRgUWJEjVG6yEtswVmQISHohjeTKDCkzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54844b4f58185be8a23e0333859eeb7512c3a7e0d4bf6680156e3fe0a4aa3a55","last_reissued_at":"2026-07-05T07:03:32.755039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:32.755039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12580","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":"2026-07-05T07:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tZ9yR8Ox4zOCgTNsSEhgbgaJaXZqPuOLg2/5Ddj6euhyh89ZCwNgR+o4tqFbKXQ9C97w5ooEfYzkkwqFY2jkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:12:34.881376Z"},"content_sha256":"ae5709f36cd10bce4e657cb8b4779bbe0f7a1d5cad71d9f1c09eeb19688fc07f","schema_version":"1.0","event_id":"sha256:ae5709f36cd10bce4e657cb8b4779bbe0f7a1d5cad71d9f1c09eeb19688fc07f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KSCEWT2YDBN6RIR6AMZYLHXLOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretraining Language Models with Text-Attributed Heterogeneous Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bowen Du, Leilei Sun, Le Yu, Tao Zou, Yifei Huang","submitted_at":"2023-10-19T08:41:21Z","abstract_excerpt":"In many real-world scenarios (e.g., academic networks, social platforms), different types of entities are not only associated with texts but also connected by various relationships, which can be abstracted as Text-Attributed Heterogeneous Graphs (TAHGs). Current pretraining tasks for Language Models (LMs) primarily focus on separately learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs. In this paper, we present a new pretraining framework for LMs that explicitly considers the topological and heterogeneous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12580","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/2310.12580/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":"2026-07-05T07:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSojym4R6zrfW9WIHrUStgX2GbRiCOnA14Eu00pbOAVTUOuROpWUJGLO0SVpARLmlqLk/lDeTiJffVfLQBw4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:12:34.881929Z"},"content_sha256":"78a6d1dadc2975719c29e552e7cd8be5643823dae31c88b93e71ba29edc66adb","schema_version":"1.0","event_id":"sha256:78a6d1dadc2975719c29e552e7cd8be5643823dae31c88b93e71ba29edc66adb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU/bundle.json","state_url":"https://pith.science/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU/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":"2026-08-05T13:12:34Z","links":{"resolver":"https://pith.science/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU","bundle":"https://pith.science/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU/bundle.json","state":"https://pith.science/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSCEWT2YDBN6RIR6AMZYLHXLOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KSCEWT2YDBN6RIR6AMZYLHXLOU","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":"0bdfa653c9add6d6d7a49e9ef9b2765a26c2bca96989fee6400598364931d9be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T08:41:21Z","title_canon_sha256":"742f9d871caf58545b4d5138dafd3b511e0856f7b35b42cd16c85a0ba7542717"},"schema_version":"1.0","source":{"id":"2310.12580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12580","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12580v2","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12580","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"KSCEWT2YDBN6","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"KSCEWT2YDBN6RIR6","created_at":"2026-07-05T07:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"KSCEWT2Y","created_at":"2026-07-05T07:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:78a6d1dadc2975719c29e552e7cd8be5643823dae31c88b93e71ba29edc66adb","target":"graph","created_at":"2026-07-05T07:03:32Z","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/2310.12580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world scenarios (e.g., academic networks, social platforms), different types of entities are not only associated with texts but also connected by various relationships, which can be abstracted as Text-Attributed Heterogeneous Graphs (TAHGs). Current pretraining tasks for Language Models (LMs) primarily focus on separately learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs. In this paper, we present a new pretraining framework for LMs that explicitly considers the topological and heterogeneous","authors_text":"Bowen Du, Leilei Sun, Le Yu, Tao Zou, Yifei Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T08:41:21Z","title":"Pretraining Language Models with Text-Attributed Heterogeneous Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12580","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:ae5709f36cd10bce4e657cb8b4779bbe0f7a1d5cad71d9f1c09eeb19688fc07f","target":"record","created_at":"2026-07-05T07:03:32Z","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":"0bdfa653c9add6d6d7a49e9ef9b2765a26c2bca96989fee6400598364931d9be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T08:41:21Z","title_canon_sha256":"742f9d871caf58545b4d5138dafd3b511e0856f7b35b42cd16c85a0ba7542717"},"schema_version":"1.0","source":{"id":"2310.12580","kind":"arxiv","version":2}},"canonical_sha256":"54844b4f58185be8a23e0333859eeb7512c3a7e0d4bf6680156e3fe0a4aa3a55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54844b4f58185be8a23e0333859eeb7512c3a7e0d4bf6680156e3fe0a4aa3a55","first_computed_at":"2026-07-05T07:03:32.755039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:32.755039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xNSnFyK8MkbRdCBo2Sim0mAP06AF/3f97yWPUtJLseN//sWfxZMxbRgUWJEjVG6yEtswVmQISHohjeTKDCkzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:32.755526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae5709f36cd10bce4e657cb8b4779bbe0f7a1d5cad71d9f1c09eeb19688fc07f","sha256:78a6d1dadc2975719c29e552e7cd8be5643823dae31c88b93e71ba29edc66adb"],"state_sha256":"45545220e835d0cc5f7f6608f886d966bd422de1e3676f62216a6b43cbd3ac4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odYqP2aDn1+ymCZ8Jk7YUP1sSStAolnPmrpcrUP3jnACSwB4P5K3tuMyKAP8Tw92p+qUuOQO90kDBKZtEh1OBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:12:34.885859Z","bundle_sha256":"44f51d9eaec11fd502c110b3e6f840c4cd549319e907f17767e06c435e15c79f"}}