{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZPPNWJBC6LBU2JE7LF2QEPYHET","short_pith_number":"pith:ZPPNWJBC","canonical_record":{"source":{"id":"2605.13032","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"884cfa273ddbca2b3722ab471c4a7852e80f52a8a04ac34f4d0093b6b50ad74e","abstract_canon_sha256":"22c3d41c0972e868d92754e2efb08855e5233e59672145b98e89ed6767afa0f6"},"schema_version":"1.0"},"canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","source":{"kind":"arxiv","id":"2605.13032","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13032","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13032v2","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13032","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZPPNWJBC6LBU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZPPNWJBC6LBU2JE7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZPPNWJBC","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZPPNWJBC6LBU2JE7LF2QEPYHET","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13032","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"884cfa273ddbca2b3722ab471c4a7852e80f52a8a04ac34f4d0093b6b50ad74e","abstract_canon_sha256":"22c3d41c0972e868d92754e2efb08855e5233e59672145b98e89ed6767afa0f6"},"schema_version":"1.0"},"canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:59.706418Z","signature_b64":"oDh86t0ht5G7gqV2fuuZyvSgD1U+rAAv+mk/gx06BrjW14fAf/QH2IU3SEZfJ85vXI0X57k8N3U/BdMM3/oUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","last_reissued_at":"2026-05-18T03:08:59.705804Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:59.705804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13032","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrsQZD/ynHWCxLKa4x/hkyMTiz0xvO/q/qMaA8D4SQMawRyhsY9gbJxX8So2BiIUq8gac5adNbwf2ogdjrrTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:35:19.570365Z"},"content_sha256":"33ceb16461cdae0f9554951f166164647a6429027c5b509fa7512690444436fb","schema_version":"1.0","event_id":"sha256:33ceb16461cdae0f9554951f166164647a6429027c5b509fa7512690444436fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZPPNWJBC6LBU2JE7LF2QEPYHET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danny Wang, Ruihong Qiu, Zi Huang","submitted_at":"2026-05-13T05:36:33Z","abstract_excerpt":"Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from either features and/or structure, leaving the model fragile under distributional changes. To address this, we propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components. TIDE "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8e7c9f5280723e3d6f52cbda363786486aba2ee10cbcd2aee818bbb5309f9d39"},"source":{"id":"2605.13032","kind":"arxiv","version":2},"verdict":{"id":"e21fc5ea-96cf-45fb-9db4-049bdf6edc16","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:37:48.342808Z","strongest_claim":"TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information.","one_line_summary":"TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy.","pith_extraction_headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection."},"references":{"count":133,"sample":[{"doi":"","year":null,"title":"Your classifier is secretly an energy based model and you should treat it like one , booktitle =","work_id":"02851fc1-372f-4f7b-b257-bf4a51cb34b6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Srikant , title =","work_id":"69a90bef-a8a1-45db-bb42-08718f01383e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"CVPR , year =","work_id":"62d26c3e-fe18-48f7-a13a-b33c009ae852","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"NeurIPS , year =","work_id":"88297c32-cee8-4ca9-a5eb-71b2c2b3160b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"NeurIPS , year =","work_id":"b2dbd2af-dfa7-4f2f-8c46-c69bc1c25f68","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":133,"snapshot_sha256":"1278d4eb508c175fc77f279873cd29b383e4d2479182613ee45e92f2d6ba2e70","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3cd33cf55920df7773abb0808e8dabac86fcd6181f24c597bcdf4f3b1df90544"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e21fc5ea-96cf-45fb-9db4-049bdf6edc16"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ZeqHMbG1PP7C17yCNHsEYiri5LFEY4Nln5rntdlvlO8ZbtLMnZ2AmyyMBsmwcQRDCLixSsxYOeEzoA5HosLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:35:19.571391Z"},"content_sha256":"8525eac7616cfa32b4afaa96d2be8ed19727a321d5212a41ec04a40c19ddf9df","schema_version":"1.0","event_id":"sha256:8525eac7616cfa32b4afaa96d2be8ed19727a321d5212a41ec04a40c19ddf9df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/bundle.json","state_url":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/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":"2026-06-10T22:35:19Z","links":{"resolver":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET","bundle":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/bundle.json","state":"https://pith.science/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPPNWJBC6LBU2JE7LF2QEPYHET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZPPNWJBC6LBU2JE7LF2QEPYHET","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":"22c3d41c0972e868d92754e2efb08855e5233e59672145b98e89ed6767afa0f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:36:33Z","title_canon_sha256":"884cfa273ddbca2b3722ab471c4a7852e80f52a8a04ac34f4d0093b6b50ad74e"},"schema_version":"1.0","source":{"id":"2605.13032","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13032","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13032v2","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13032","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZPPNWJBC6LBU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZPPNWJBC6LBU2JE7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZPPNWJBC","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8525eac7616cfa32b4afaa96d2be8ed19727a321d5212a41ec04a40c19ddf9df","target":"graph","created_at":"2026-05-18T03:08:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection."}],"snapshot_sha256":"8e7c9f5280723e3d6f52cbda363786486aba2ee10cbcd2aee818bbb5309f9d39"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3cd33cf55920df7773abb0808e8dabac86fcd6181f24c597bcdf4f3b1df90544"},"paper":{"abstract_excerpt":"Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure. Prior work established that methods trained with standard supervised learning (SL) objectives tend to capture spurious signals from either features and/or structure, leaving the model fragile under distributional changes. To address this, we propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components. TIDE ","authors_text":"Danny Wang, Ruihong Qiu, Zi Huang","cross_cats":[],"headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:36:33Z","title":"What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition"},"references":{"count":133,"internal_anchors":0,"resolved_work":133,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Your classifier is secretly an energy based model and you should treat it like one , booktitle =","work_id":"02851fc1-372f-4f7b-b257-bf4a51cb34b6","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Srikant , title =","work_id":"69a90bef-a8a1-45db-bb42-08718f01383e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"CVPR , year =","work_id":"62d26c3e-fe18-48f7-a13a-b33c009ae852","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"NeurIPS , year =","work_id":"88297c32-cee8-4ca9-a5eb-71b2c2b3160b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"NeurIPS , year =","work_id":"b2dbd2af-dfa7-4f2f-8c46-c69bc1c25f68","year":null}],"snapshot_sha256":"1278d4eb508c175fc77f279873cd29b383e4d2479182613ee45e92f2d6ba2e70"},"source":{"id":"2605.13032","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T05:37:48.342808Z","id":"e21fc5ea-96cf-45fb-9db4-049bdf6edc16","model_set":{"reader":"grok-4.3"},"one_line_summary":"TIDE decomposes graph information into feature-specific, structure-specific, and joint components to retain only label-relevant joint signals and improve OOD detection over standard supervised learning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TIDE decomposes graph information into feature-specific, structure-specific and joint components to retain only label-relevant joint signals for improved out-of-distribution node detection.","strongest_claim":"TIDE explicitly decomposes information into feature-specific, structure-specific and joint components, preserving only the label-relevant part of the joint information while filtering out spurious feature- and structure-specific information.","weakest_assumption":"That the joint information component can be reliably separated into label-relevant versus spurious parts and that removing the spurious specific components will produce a measurable entropy gap and higher ID confidence without harming ID accuracy."}},"verdict_id":"e21fc5ea-96cf-45fb-9db4-049bdf6edc16"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:33ceb16461cdae0f9554951f166164647a6429027c5b509fa7512690444436fb","target":"record","created_at":"2026-05-18T03:08:59Z","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":"22c3d41c0972e868d92754e2efb08855e5233e59672145b98e89ed6767afa0f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T05:36:33Z","title_canon_sha256":"884cfa273ddbca2b3722ab471c4a7852e80f52a8a04ac34f4d0093b6b50ad74e"},"schema_version":"1.0","source":{"id":"2605.13032","kind":"arxiv","version":2}},"canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbdedb2422f2c34d249f5975023f0724fa93b3f0d26a9f96726a97fd456f49e2","first_computed_at":"2026-05-18T03:08:59.705804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:59.705804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oDh86t0ht5G7gqV2fuuZyvSgD1U+rAAv+mk/gx06BrjW14fAf/QH2IU3SEZfJ85vXI0X57k8N3U/BdMM3/oUBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:59.706418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13032","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33ceb16461cdae0f9554951f166164647a6429027c5b509fa7512690444436fb","sha256:8525eac7616cfa32b4afaa96d2be8ed19727a321d5212a41ec04a40c19ddf9df"],"state_sha256":"0017d90108a7bdf946c2253c0f9ab61a6cb1d6941f31081975e5822a2765c0da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ntq1eVIhydLgLO/kgJVuflmefvps56zwJE3qiHBDbbBc/q2E1UMW/hdr9YLnMLpK/Lkg8T7yEhedUwGKgqHUDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T22:35:19.574786Z","bundle_sha256":"acceae78b10005c1f4b221a24c4f5cdb91b5a6f3ada979704892721b6c18a88a"}}