{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7URYAVRGCVLWL2URBRAXBIDEJS","short_pith_number":"pith:7URYAVRG","schema_version":"1.0","canonical_sha256":"fd23805626155765ea910c4170a0644cadaec84331c52f2006a42c997c0d7920","source":{"kind":"arxiv","id":"2601.22384","version":2},"attestation_state":"computed","paper":{"title":"Graph is a Substrate Across Data Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuxu Zhang, Jiazheng Li, Jinhe Bi, Xiaoming Wu, Yanfang Ye, Yijun Tian, Yunpu Ma, Zehong Wang, Ziming Li","submitted_at":"2026-01-29T22:46:02Z","abstract_excerpt":"Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and task-isolated manner, where graph representations are constructed within individual task contexts and discarded thereafter. As a result, structural regularities across modalities and tasks are repeatedly reconstructed rather than accumulated at the level of intermediate graph representations. This motivates a representation-learning question: how should graph structure be organized so that it can persist and accumulat"},"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":"2601.22384","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T22:46:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ed13099fb0138b66a1b9d19b07dd9f387d0ea428eac6fdf84d006839cb507ba","abstract_canon_sha256":"c04e5dd1fce0b56905ec4c6134cf0ff27c040881df5e7c3881e1523823eb438a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:43.458380Z","signature_b64":"nhija7TXyXLq4p0MFB4GjjNsnjSMX7E2TEDpLJmYGaotkCqCXKBOwfLh+1wA4oqygSAMK9DWSLxyiOEJwMUnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd23805626155765ea910c4170a0644cadaec84331c52f2006a42c997c0d7920","last_reissued_at":"2026-05-27T01:05:43.457611Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:43.457611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph is a Substrate Across Data Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuxu Zhang, Jiazheng Li, Jinhe Bi, Xiaoming Wu, Yanfang Ye, Yijun Tian, Yunpu Ma, Zehong Wang, Ziming Li","submitted_at":"2026-01-29T22:46:02Z","abstract_excerpt":"Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and task-isolated manner, where graph representations are constructed within individual task contexts and discarded thereafter. As a result, structural regularities across modalities and tasks are repeatedly reconstructed rather than accumulated at the level of intermediate graph representations. This motivates a representation-learning question: how should graph structure be organized so that it can persist and accumulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22384","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/2601.22384/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":"2601.22384","created_at":"2026-05-27T01:05:43.457729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22384v2","created_at":"2026-05-27T01:05:43.457729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22384","created_at":"2026-05-27T01:05:43.457729+00:00"},{"alias_kind":"pith_short_12","alias_value":"7URYAVRGCVLW","created_at":"2026-05-27T01:05:43.457729+00:00"},{"alias_kind":"pith_short_16","alias_value":"7URYAVRGCVLWL2UR","created_at":"2026-05-27T01:05:43.457729+00:00"},{"alias_kind":"pith_short_8","alias_value":"7URYAVRG","created_at":"2026-05-27T01:05:43.457729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.21801","citing_title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06576","citing_title":"On the Safety of Graph Representation Learning","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS","json":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS.json","graph_json":"https://pith.science/api/pith-number/7URYAVRGCVLWL2URBRAXBIDEJS/graph.json","events_json":"https://pith.science/api/pith-number/7URYAVRGCVLWL2URBRAXBIDEJS/events.json","paper":"https://pith.science/paper/7URYAVRG"},"agent_actions":{"view_html":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS","download_json":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS.json","view_paper":"https://pith.science/paper/7URYAVRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22384&json=true","fetch_graph":"https://pith.science/api/pith-number/7URYAVRGCVLWL2URBRAXBIDEJS/graph.json","fetch_events":"https://pith.science/api/pith-number/7URYAVRGCVLWL2URBRAXBIDEJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS/action/storage_attestation","attest_author":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS/action/author_attestation","sign_citation":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS/action/citation_signature","submit_replication":"https://pith.science/pith/7URYAVRGCVLWL2URBRAXBIDEJS/action/replication_record"}},"created_at":"2026-05-27T01:05:43.457729+00:00","updated_at":"2026-05-27T01:05:43.457729+00:00"}