{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5WLHAXJX6KQWZJCZRFXNSEXSJB","short_pith_number":"pith:5WLHAXJX","schema_version":"1.0","canonical_sha256":"ed96705d37f2a16ca459896ed912f24843ebeb683afd6dd404d071f56b24c240","source":{"kind":"arxiv","id":"2606.31166","version":1},"attestation_state":"computed","paper":{"title":"TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hanghang Tong, Haobo Xu, Lingjie Chen, Yanjun Zhao, Yuanchen Bei, Yuzhong Chen","submitted_at":"2026-06-30T05:56:18Z","abstract_excerpt":"Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and graphs use the language model mainly as a text encoder and delegate structure learning to a separate graph module. We propose method that unifies textual reasoning and graph message passing within a masked diffusion language model, a language model with bidirectional attention and generative decoding. F"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.31166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T05:56:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"593bee77911424606818bdcc04c857c5ae46ae2e543772c19ec70a0dd2932af2","abstract_canon_sha256":"0fd3f0d64f94b6cc53d42a14ef5ae91dd0bdb81d1eeecc5009a13dfc150244f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:30.992134Z","signature_b64":"MNYieJy2C7YnvNsm6m1e8nkCRVToYVQwiJnrCsmOFSbM51QjdxMssEbJc2oFHCUKdAVQcUtdj2uT16AR6MvLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed96705d37f2a16ca459896ed912f24843ebeb683afd6dd404d071f56b24c240","last_reissued_at":"2026-07-01T01:17:30.991747Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:30.991747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hanghang Tong, Haobo Xu, Lingjie Chen, Yanjun Zhao, Yuanchen Bei, Yuzhong Chen","submitted_at":"2026-06-30T05:56:18Z","abstract_excerpt":"Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and graphs use the language model mainly as a text encoder and delegate structure learning to a separate graph module. We propose method that unifies textual reasoning and graph message passing within a masked diffusion language model, a language model with bidirectional attention and generative decoding. F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31166","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/2606.31166/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.31166","created_at":"2026-07-01T01:17:30.991803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31166v1","created_at":"2026-07-01T01:17:30.991803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31166","created_at":"2026-07-01T01:17:30.991803+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WLHAXJX6KQW","created_at":"2026-07-01T01:17:30.991803+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WLHAXJX6KQWZJCZ","created_at":"2026-07-01T01:17:30.991803+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WLHAXJX","created_at":"2026-07-01T01:17:30.991803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB","json":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB.json","graph_json":"https://pith.science/api/pith-number/5WLHAXJX6KQWZJCZRFXNSEXSJB/graph.json","events_json":"https://pith.science/api/pith-number/5WLHAXJX6KQWZJCZRFXNSEXSJB/events.json","paper":"https://pith.science/paper/5WLHAXJX"},"agent_actions":{"view_html":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB","download_json":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB.json","view_paper":"https://pith.science/paper/5WLHAXJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31166&json=true","fetch_graph":"https://pith.science/api/pith-number/5WLHAXJX6KQWZJCZRFXNSEXSJB/graph.json","fetch_events":"https://pith.science/api/pith-number/5WLHAXJX6KQWZJCZRFXNSEXSJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB/action/storage_attestation","attest_author":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB/action/author_attestation","sign_citation":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB/action/citation_signature","submit_replication":"https://pith.science/pith/5WLHAXJX6KQWZJCZRFXNSEXSJB/action/replication_record"}},"created_at":"2026-07-01T01:17:30.991803+00:00","updated_at":"2026-07-01T01:17:30.991803+00:00"}