{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WAVR2PVTQZYGSRID44X5PPAQRJ","short_pith_number":"pith:WAVR2PVT","canonical_record":{"source":{"id":"2607.28397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T15:49:34Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"9215e799ee4a9e84d14c879dea63bcfd07218d31810be300a8abb6c8a19c4f8b","abstract_canon_sha256":"ee867d7ce368cbe41704b90d6aeaf5614af5b7a328a59433c038b6ecf74d6156"},"schema_version":"1.0"},"canonical_sha256":"b02b1d3eb38670694503e72fd7bc108a73e56f5350130d389d7f45bbdd726de2","source":{"kind":"arxiv","id":"2607.28397","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28397","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28397v1","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28397","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"WAVR2PVTQZYG","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"WAVR2PVTQZYGSRID","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"WAVR2PVT","created_at":"2026-07-31T01:37:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WAVR2PVTQZYGSRID44X5PPAQRJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T15:49:34Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"9215e799ee4a9e84d14c879dea63bcfd07218d31810be300a8abb6c8a19c4f8b","abstract_canon_sha256":"ee867d7ce368cbe41704b90d6aeaf5614af5b7a328a59433c038b6ecf74d6156"},"schema_version":"1.0"},"canonical_sha256":"b02b1d3eb38670694503e72fd7bc108a73e56f5350130d389d7f45bbdd726de2","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b02b1d3eb38670694503e72fd7bc108a73e56f5350130d389d7f45bbdd726de2","last_reissued_at":"2026-07-31T01:37:31.676997Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:31.676997Z"},"source_kind":"arxiv","source_id":"2607.28397","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":"2026-07-31T01:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZQX7w158kNDlDq2XvpWbUpRQ25+LJk2Yd0NsqFrK2Gm6pEf852E5fRRKgCSVPgTMGhfhaq5gMRQriJrovLZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:59:45.318400Z"},"content_sha256":"3b70f205aa34a702fbe8a4269866110406786244baf0e50b461453dd4bdfc777","schema_version":"1.0","event_id":"sha256:3b70f205aa34a702fbe8a4269866110406786244baf0e50b461453dd4bdfc777"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WAVR2PVTQZYGSRID44X5PPAQRJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Anette Frank, Beni Egressy, Johann Higl, Maya Arseven, Moritz Plenz","submitted_at":"2026-07-30T15:49:34Z","abstract_excerpt":"Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approaches have explored graph neural network (GNN)-based retrievers to model graph topology in multi-hop reasoning tasks. In parallel, graph language models (GLMs) have emerged as a promising paradigm that integrates graph reasoning and the semantic capabilities of language models. In this work, we introduce a GLM-based retriever and investigate the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28397","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/2607.28397/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":"2026-07-31T01:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BpJS2Vp9VICilI/LXVp6YzS8G5c/9dP0VtYx4XeHn76kym/BEtHsnPr2sEmwpVGYEhCGnKN40yTzP5JbOKWLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:59:45.319193Z"},"content_sha256":"b6ea3c4fa5466656bb206f744b4316060b81866cff66a983f02310f53bf1602d","schema_version":"1.0","event_id":"sha256:b6ea3c4fa5466656bb206f744b4316060b81866cff66a983f02310f53bf1602d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAVR2PVTQZYGSRID44X5PPAQRJ/bundle.json","state_url":"https://pith.science/pith/WAVR2PVTQZYGSRID44X5PPAQRJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAVR2PVTQZYGSRID44X5PPAQRJ/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":"2026-08-04T00:59:45Z","links":{"resolver":"https://pith.science/pith/WAVR2PVTQZYGSRID44X5PPAQRJ","bundle":"https://pith.science/pith/WAVR2PVTQZYGSRID44X5PPAQRJ/bundle.json","state":"https://pith.science/pith/WAVR2PVTQZYGSRID44X5PPAQRJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAVR2PVTQZYGSRID44X5PPAQRJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WAVR2PVTQZYGSRID44X5PPAQRJ","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":"ee867d7ce368cbe41704b90d6aeaf5614af5b7a328a59433c038b6ecf74d6156","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T15:49:34Z","title_canon_sha256":"9215e799ee4a9e84d14c879dea63bcfd07218d31810be300a8abb6c8a19c4f8b"},"schema_version":"1.0","source":{"id":"2607.28397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28397","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28397v1","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28397","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"WAVR2PVTQZYG","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"WAVR2PVTQZYGSRID","created_at":"2026-07-31T01:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"WAVR2PVT","created_at":"2026-07-31T01:37:31Z"}],"graph_snapshots":[{"event_id":"sha256:b6ea3c4fa5466656bb206f744b4316060b81866cff66a983f02310f53bf1602d","target":"graph","created_at":"2026-07-31T01:37:31Z","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/2607.28397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic information. Recent approaches have explored graph neural network (GNN)-based retrievers to model graph topology in multi-hop reasoning tasks. In parallel, graph language models (GLMs) have emerged as a promising paradigm that integrates graph reasoning and the semantic capabilities of language models. In this work, we introduce a GLM-based retriever and investigate the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based re","authors_text":"Anette Frank, Beni Egressy, Johann Higl, Maya Arseven, Moritz Plenz","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T15:49:34Z","title":"GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28397","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":"sha256:3b70f205aa34a702fbe8a4269866110406786244baf0e50b461453dd4bdfc777","target":"record","created_at":"2026-07-31T01:37:31Z","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":"ee867d7ce368cbe41704b90d6aeaf5614af5b7a328a59433c038b6ecf74d6156","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T15:49:34Z","title_canon_sha256":"9215e799ee4a9e84d14c879dea63bcfd07218d31810be300a8abb6c8a19c4f8b"},"schema_version":"1.0","source":{"id":"2607.28397","kind":"arxiv","version":1}},"canonical_sha256":"b02b1d3eb38670694503e72fd7bc108a73e56f5350130d389d7f45bbdd726de2","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b02b1d3eb38670694503e72fd7bc108a73e56f5350130d389d7f45bbdd726de2","first_computed_at":"2026-07-31T01:37:31.676997Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:31.676997Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b70f205aa34a702fbe8a4269866110406786244baf0e50b461453dd4bdfc777","sha256:b6ea3c4fa5466656bb206f744b4316060b81866cff66a983f02310f53bf1602d"],"state_sha256":"b896ef7ae95977d5033f5b91a650236b9927fadf2f87c7fe144adbe5d4ddd094"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXg007fRk3vJoFsHFUy8HGP9r0/ZrryqGbTIbXWTxOnAyDYs8AoFtTxE1rhwbBNU3Nj04oVMzMQGT5q3bY2PDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:59:45.324543Z","bundle_sha256":"9e00cab1221fc7b85fa4196cd664b046e4c5323333e461f9ab5cfad085524554"}}