{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YI5HGQEBJGOYNVLZGKDAHWZQGM","short_pith_number":"pith:YI5HGQEB","canonical_record":{"source":{"id":"2607.27303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T17:04:30Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"a2d8b467774703d71eb833e0034c0624e66d5d6fa7201a278ec4a458d2e4b606","abstract_canon_sha256":"fb142cdd34c8bf988c1625e46339536fbf94c81b8d53929aa5881b99cb830f06"},"schema_version":"1.0"},"canonical_sha256":"c23a734081499d86d579328603db30333cda97a275edbce00bc52896ec154372","source":{"kind":"arxiv","id":"2607.27303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27303","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27303v1","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27303","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"YI5HGQEBJGOY","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"YI5HGQEBJGOYNVLZ","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"YI5HGQEB","created_at":"2026-07-31T00:10:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YI5HGQEBJGOYNVLZGKDAHWZQGM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T17:04:30Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"a2d8b467774703d71eb833e0034c0624e66d5d6fa7201a278ec4a458d2e4b606","abstract_canon_sha256":"fb142cdd34c8bf988c1625e46339536fbf94c81b8d53929aa5881b99cb830f06"},"schema_version":"1.0"},"canonical_sha256":"c23a734081499d86d579328603db30333cda97a275edbce00bc52896ec154372","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c23a734081499d86d579328603db30333cda97a275edbce00bc52896ec154372","last_reissued_at":"2026-07-31T00:10:33.163751Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:33.163751Z"},"source_kind":"arxiv","source_id":"2607.27303","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":"2026-07-31T00:10:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qJBW1hl/KR8V1xCgLm/dMpyEyNjeek2y6vKytTIMSGk8KRrsbw84610CxWeMUuUODih00oCmeuquUHR4diiRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:59:38.374189Z"},"content_sha256":"964a1ac3e64c70f117ad6eb8be6e3950347cc6d5870051316edce1f481032642","schema_version":"1.0","event_id":"sha256:964a1ac3e64c70f117ad6eb8be6e3950347cc6d5870051316edce1f481032642"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YI5HGQEBJGOYNVLZGKDAHWZQGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Diego Collarana, Er Jin, Stefan Decker, Yixin Peng","submitted_at":"2026-07-29T17:04:30Z","abstract_excerpt":"Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time. Learning on such graphs requires jointly modeling cross-type structural heterogeneity and the temporal dynamics of interactions, yet existing methods still struggle to reconcile parameter-efficient cross-type transfer with relation-aware specialization, and typically inject time only as additive features outside the attention kernel. We propose \\textbf{THGFM}, a web-scale temporal heterogeneous graph fusion model that addresses both li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27303","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/2607.27303/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":"2026-07-31T00:10:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QkePMY4JuGi6RTGOPNJEanqUcJmj7uyC4GcH9QRCxA0JB3iqL8eQ7QWd1DN9gskx/tqliFmlVWEeAT1V15gZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:59:38.374791Z"},"content_sha256":"eafbc5fd127d1c0ac0342a3877b7bfdcb25baebb6eca3e45f34f000048e677ea","schema_version":"1.0","event_id":"sha256:eafbc5fd127d1c0ac0342a3877b7bfdcb25baebb6eca3e45f34f000048e677ea"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YI5HGQEBJGOYNVLZGKDAHWZQGM","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TKDE.2022.3160208) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Yu, L., Sun, L., Du, B., Liu, C., Lv, W., Xiong, H.: Heterogeneous graph repre- sentation learning with relation awareness. IEEE Transactions on Knowledge and Data Engineering35(6), 5935–5947 (2023), https://doi.org/10.1109/TKDE.2022. 31602","arxiv_id":"2607.27303","detector":"doi_compliance","evidence":{"ref_index":28,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/tkde.2022","reconstructed_doi":"10.1109/TKDE.2022.3160208"},"severity":"advisory","ref_index":28,"audited_at":"2026-08-01T10:08:02.381991Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TKDE.2022.3160208","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5fce5601cdf9f2762b67ae33f3d9e299b0516100b1ab0132699dc3b6dd4e7a08","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15581,"payload_sha256":"2c88cc106307068221187b48e6f0036e33f49ed4fa197bc9688fceb3b9622d9f","signature_b64":"Grj4Mt/ekPDndhYzQ/QAZ3GLSbwj3iPtb71PGv0WDTqvHdYx85et6gd34sO86sCXHyqfCVt71wq9zJbEUuhgBQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T10:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6joGYLmIRGvB59MgRdQAbVaRTWBVzwrEridD4UKdKSHu9xSUfgLY0UmRIMtbk0mFtKP7PYoL89T9432drwwYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:59:38.379485Z"},"content_sha256":"358669700081c9150911f267d5a706f3d39d037f6c35a6115c354aa20a56eb2b","schema_version":"1.0","event_id":"sha256:358669700081c9150911f267d5a706f3d39d037f6c35a6115c354aa20a56eb2b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YI5HGQEBJGOYNVLZGKDAHWZQGM","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TKDE.2021.3101356) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Yang, Y., Guan, Z., Li, J., Zhao, W., Cui, J., Wang, Q.: Interpretable and efficient heterogeneous graph convolutional network. IEEE Transactions on Knowledge and Data Engineering35(2), 1637–1650 (2023), https://doi.org/10.1109/TKDE.2021. 3","arxiv_id":"2607.27303","detector":"doi_compliance","evidence":{"ref_index":26,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/tkde.2021","reconstructed_doi":"10.1109/TKDE.2021.3101356"},"severity":"advisory","ref_index":26,"audited_at":"2026-08-01T10:08:02.381991Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TKDE.2021.3101356","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"8fba1b1fca56fcc435e4c002e9b37797099a8c078481b184b6b08bef12c37d02","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15580,"payload_sha256":"78bab8419869f6a18822af466e01983c5ba26e80696659ca5288b459597c5818","signature_b64":"u1l3XoKL6HvtSWutzq6QmcqvkCLqLpKLx0GpKGk8LB2P0B9+u2NXgM8pPEPDVw+HlPEBJv0hnOI3AOs7jemPDg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T10:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkWWkzsy74tFWAy9CNgipdEs5ngbALRw5Cy7ddQV3p4/A/6tzFyPyqyykh3cE6Qkc/IBfj0j00UqWLjwPtR0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:59:38.379870Z"},"content_sha256":"f9ded5035f29a448dea9027cb246a2fdfe26db95ae8b650b2c430ec2e57fe3c4","schema_version":"1.0","event_id":"sha256:f9ded5035f29a448dea9027cb246a2fdfe26db95ae8b650b2c430ec2e57fe3c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM/bundle.json","state_url":"https://pith.science/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM/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":"2026-08-18T09:59:38Z","links":{"resolver":"https://pith.science/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM","bundle":"https://pith.science/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM/bundle.json","state":"https://pith.science/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YI5HGQEBJGOYNVLZGKDAHWZQGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YI5HGQEBJGOYNVLZGKDAHWZQGM","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fb142cdd34c8bf988c1625e46339536fbf94c81b8d53929aa5881b99cb830f06","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T17:04:30Z","title_canon_sha256":"a2d8b467774703d71eb833e0034c0624e66d5d6fa7201a278ec4a458d2e4b606"},"schema_version":"1.0","source":{"id":"2607.27303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27303","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27303v1","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27303","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"YI5HGQEBJGOY","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"YI5HGQEBJGOYNVLZ","created_at":"2026-07-31T00:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"YI5HGQEB","created_at":"2026-07-31T00:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:eafbc5fd127d1c0ac0342a3877b7bfdcb25baebb6eca3e45f34f000048e677ea","target":"graph","created_at":"2026-07-31T00:10:33Z","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/2607.27303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time. Learning on such graphs requires jointly modeling cross-type structural heterogeneity and the temporal dynamics of interactions, yet existing methods still struggle to reconcile parameter-efficient cross-type transfer with relation-aware specialization, and typically inject time only as additive features outside the attention kernel. We propose \\textbf{THGFM}, a web-scale temporal heterogeneous graph fusion model that addresses both li","authors_text":"Diego Collarana, Er Jin, Stefan Decker, Yixin Peng","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T17:04:30Z","title":"THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27303","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":"sha256:964a1ac3e64c70f117ad6eb8be6e3950347cc6d5870051316edce1f481032642","target":"record","created_at":"2026-07-31T00:10:33Z","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":"fb142cdd34c8bf988c1625e46339536fbf94c81b8d53929aa5881b99cb830f06","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T17:04:30Z","title_canon_sha256":"a2d8b467774703d71eb833e0034c0624e66d5d6fa7201a278ec4a458d2e4b606"},"schema_version":"1.0","source":{"id":"2607.27303","kind":"arxiv","version":1}},"canonical_sha256":"c23a734081499d86d579328603db30333cda97a275edbce00bc52896ec154372","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c23a734081499d86d579328603db30333cda97a275edbce00bc52896ec154372","first_computed_at":"2026-07-31T00:10:33.163751Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T00:10:33.163751Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27303","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:358669700081c9150911f267d5a706f3d39d037f6c35a6115c354aa20a56eb2b","sha256:f9ded5035f29a448dea9027cb246a2fdfe26db95ae8b650b2c430ec2e57fe3c4"]}],"invalid_events":[],"applied_event_ids":["sha256:964a1ac3e64c70f117ad6eb8be6e3950347cc6d5870051316edce1f481032642","sha256:eafbc5fd127d1c0ac0342a3877b7bfdcb25baebb6eca3e45f34f000048e677ea"],"state_sha256":"4e3af8afb891739427cbacf119b8509561cd7e32b739a5d3c1c67ec2c51da4be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQYBYPjUX9QgnvjgXRIinpx1OrP9BrDpwokGyMiQltBzeXvFK1lgr/9+uHAR5BsiUC/fSWj6lX/ByLrxHMxyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:59:38.382627Z","bundle_sha256":"29c78fc864483505b5611b4f4d0ed79772e36ba8db88eec553727d7e2b485c30"}}