{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V6JJZX7THGL3UXJTZMDNZ743W6","short_pith_number":"pith:V6JJZX7T","schema_version":"1.0","canonical_sha256":"af929cdff33997ba5d33cb06dcff9bb7842122c44bfceb3d2bac5e7402fb7412","source":{"kind":"arxiv","id":"2606.11831","version":1},"attestation_state":"computed","paper":{"title":"From Uniform to Learned Graph Priors: Diffusion for Structure Discovery","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Duxin Chen, Hao Guo, Jiawen Chen, Qi Shao, Wenwu Yu","submitted_at":"2026-06-10T09:14:45Z","abstract_excerpt":"Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges. However, these methods typically rely on oversimplified, factorized graph priors. Such priors, typically nearing uniform distributions, treat edges as independent entities. This systemic misalignment does not match the real-world systems and yields diffuse and indecisive edge posteriors limiting the reliability of structural discovery. To address this, we propose \\textit{Diff-prior}, a diffusion-parameterized adaptive prior used to calibrate latent "},"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":"2606.11831","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T09:14:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3bd0f7ebcacb3965c4dc1a612d1cf0096d5ddd263eb2a4a10aa245738d3da13c","abstract_canon_sha256":"e20ab6c200bca8b15b743ccbc813c72e0451c116f39244c2fb4608694428f1cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:10.646168Z","signature_b64":"sWTol7dF6nzPDu/IvHjSJiGy5HI2Z+Z2Xn7ptQu+70WR4UvgpGHO3tHLVzj+3g+rKHEopqci7tM6D/OfUI4mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af929cdff33997ba5d33cb06dcff9bb7842122c44bfceb3d2bac5e7402fb7412","last_reissued_at":"2026-06-11T01:10:10.645336Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:10.645336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Uniform to Learned Graph Priors: Diffusion for Structure Discovery","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Duxin Chen, Hao Guo, Jiawen Chen, Qi Shao, Wenwu Yu","submitted_at":"2026-06-10T09:14:45Z","abstract_excerpt":"Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges. However, these methods typically rely on oversimplified, factorized graph priors. Such priors, typically nearing uniform distributions, treat edges as independent entities. This systemic misalignment does not match the real-world systems and yields diffuse and indecisive edge posteriors limiting the reliability of structural discovery. To address this, we propose \\textit{Diff-prior}, a diffusion-parameterized adaptive prior used to calibrate latent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11831","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/2606.11831/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":"2606.11831","created_at":"2026-06-11T01:10:10.645475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11831v1","created_at":"2026-06-11T01:10:10.645475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11831","created_at":"2026-06-11T01:10:10.645475+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6JJZX7THGL3","created_at":"2026-06-11T01:10:10.645475+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6JJZX7THGL3UXJT","created_at":"2026-06-11T01:10:10.645475+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6JJZX7T","created_at":"2026-06-11T01:10:10.645475+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/V6JJZX7THGL3UXJTZMDNZ743W6","json":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6.json","graph_json":"https://pith.science/api/pith-number/V6JJZX7THGL3UXJTZMDNZ743W6/graph.json","events_json":"https://pith.science/api/pith-number/V6JJZX7THGL3UXJTZMDNZ743W6/events.json","paper":"https://pith.science/paper/V6JJZX7T"},"agent_actions":{"view_html":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6","download_json":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6.json","view_paper":"https://pith.science/paper/V6JJZX7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11831&json=true","fetch_graph":"https://pith.science/api/pith-number/V6JJZX7THGL3UXJTZMDNZ743W6/graph.json","fetch_events":"https://pith.science/api/pith-number/V6JJZX7THGL3UXJTZMDNZ743W6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6/action/storage_attestation","attest_author":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6/action/author_attestation","sign_citation":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6/action/citation_signature","submit_replication":"https://pith.science/pith/V6JJZX7THGL3UXJTZMDNZ743W6/action/replication_record"}},"created_at":"2026-06-11T01:10:10.645475+00:00","updated_at":"2026-06-11T01:10:10.645475+00:00"}