{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2MS7PWLABODDGDW3FTTXPSF3AO","short_pith_number":"pith:2MS7PWLA","schema_version":"1.0","canonical_sha256":"d325f7d9600b86330edb2ce777c8bb039a2aa2f9c0658c73fbe08767a571e840","source":{"kind":"arxiv","id":"2308.13212","version":2},"attestation_state":"computed","paper":{"title":"SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fugee Tsung, Haihong Zhao, Jia Li, Jiashun Cheng, Peilin Zhao, Tingyang Xu, Yang Liu, Yu Rong","submitted_at":"2023-08-25T07:15:58Z","abstract_excerpt":"Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate consideration of physical inductive biases: (1) Existing studies overlook the continuity of transitions among system states, opting to employ several discrete transformation layers to learn the direct mapping between two adjacent states; (2) Most models only account for first-order velocity information, despite the fact that many physical systems are governed by second-order mot"},"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":"2308.13212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-25T07:15:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a38f6afa95b1e2b0330a103d7c0008647a062eb790d6e138f7fc49c448e4d3a","abstract_canon_sha256":"6a95d90a26f34a55df8e98e3e2f1745cce601273b75b1b64459a1195b0f7c5cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:50.304632Z","signature_b64":"vEIikRSoJ6uSTnYCQtqM8w+H7Q6GFXrrLVicOEJ1nvPmVPYJWsIsd4Mn7LAQyxc9xWlgX80JUA+KUj4AszmnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d325f7d9600b86330edb2ce777c8bb039a2aa2f9c0658c73fbe08767a571e840","last_reissued_at":"2026-07-05T07:54:50.304190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:50.304190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fugee Tsung, Haihong Zhao, Jia Li, Jiashun Cheng, Peilin Zhao, Tingyang Xu, Yang Liu, Yu Rong","submitted_at":"2023-08-25T07:15:58Z","abstract_excerpt":"Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate consideration of physical inductive biases: (1) Existing studies overlook the continuity of transitions among system states, opting to employ several discrete transformation layers to learn the direct mapping between two adjacent states; (2) Most models only account for first-order velocity information, despite the fact that many physical systems are governed by second-order mot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13212","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/2308.13212/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":"2308.13212","created_at":"2026-07-05T07:54:50.304246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13212v2","created_at":"2026-07-05T07:54:50.304246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13212","created_at":"2026-07-05T07:54:50.304246+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MS7PWLABODD","created_at":"2026-07-05T07:54:50.304246+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MS7PWLABODDGDW3","created_at":"2026-07-05T07:54:50.304246+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MS7PWLA","created_at":"2026-07-05T07:54:50.304246+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/2MS7PWLABODDGDW3FTTXPSF3AO","json":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO.json","graph_json":"https://pith.science/api/pith-number/2MS7PWLABODDGDW3FTTXPSF3AO/graph.json","events_json":"https://pith.science/api/pith-number/2MS7PWLABODDGDW3FTTXPSF3AO/events.json","paper":"https://pith.science/paper/2MS7PWLA"},"agent_actions":{"view_html":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO","download_json":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO.json","view_paper":"https://pith.science/paper/2MS7PWLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13212&json=true","fetch_graph":"https://pith.science/api/pith-number/2MS7PWLABODDGDW3FTTXPSF3AO/graph.json","fetch_events":"https://pith.science/api/pith-number/2MS7PWLABODDGDW3FTTXPSF3AO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO/action/storage_attestation","attest_author":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO/action/author_attestation","sign_citation":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO/action/citation_signature","submit_replication":"https://pith.science/pith/2MS7PWLABODDGDW3FTTXPSF3AO/action/replication_record"}},"created_at":"2026-07-05T07:54:50.304246+00:00","updated_at":"2026-07-05T07:54:50.304246+00:00"}