{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JRI3YRNXYXNJJMLISAVBVXJR64","short_pith_number":"pith:JRI3YRNX","canonical_record":{"source":{"id":"2305.05577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T21:48:31Z","cross_cats_sorted":[],"title_canon_sha256":"7961b437c554aa58c6e28458c4e5fdfddd2c142783e9eb82d69a3a8c85b1ee6f","abstract_canon_sha256":"8bd233e22e3f5fc7abf6bdc62e51b52d9fa3ffa9b6b55e30268a6046458b06a7"},"schema_version":"1.0"},"canonical_sha256":"4c51bc45b7c5da94b168902a1add31f733ea42b85c97536cf2d423bf1c94faa0","source":{"kind":"arxiv","id":"2305.05577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05577","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05577v1","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05577","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"JRI3YRNXYXNJ","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"JRI3YRNXYXNJJMLI","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"JRI3YRNX","created_at":"2026-07-05T06:08:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JRI3YRNXYXNJJMLISAVBVXJR64","target":"record","payload":{"canonical_record":{"source":{"id":"2305.05577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T21:48:31Z","cross_cats_sorted":[],"title_canon_sha256":"7961b437c554aa58c6e28458c4e5fdfddd2c142783e9eb82d69a3a8c85b1ee6f","abstract_canon_sha256":"8bd233e22e3f5fc7abf6bdc62e51b52d9fa3ffa9b6b55e30268a6046458b06a7"},"schema_version":"1.0"},"canonical_sha256":"4c51bc45b7c5da94b168902a1add31f733ea42b85c97536cf2d423bf1c94faa0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:36.430433Z","signature_b64":"U38tCBJhU6YubE/l6oJ33aGy+5/XM7ogVwymQ+VUMAOUqlMSAWBXYOeQiibrgEAXtp0up0tWotxpyWRASzq2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c51bc45b7c5da94b168902a1add31f733ea42b85c97536cf2d423bf1c94faa0","last_reissued_at":"2026-07-05T06:08:36.429946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:36.429946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.05577","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXyvWe87rPP6P+6nS6hPGrDlSjP840pOZgMJmyt3xXeLXu+pAiX8eAUC4hQ2NYMLuD24fQ1D6hAmjk/truEDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:13:25.428375Z"},"content_sha256":"af4af41d42f67c9bea42f262ac6fd159b812c025ae47516eff9f624ea2734030","schema_version":"1.0","event_id":"sha256:af4af41d42f67c9bea42f262ac6fd159b812c025ae47516eff9f624ea2734030"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JRI3YRNXYXNJJMLISAVBVXJR64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FAENet: Frame Averaging Equivariant GNN for Materials Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Duval, Alex Hernandez Garcia, David Rolnick, Fragkiskos D. Malliaros, Santiago Miret, Victor Schmidt, Yoshua Bengio","submitted_at":"2023-04-28T21:48:31Z","abstract_excerpt":"Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they enforce symmetries via the model architecture, which often reduces their expressivity, scalability and comprehensibility. In this paper, we introduce (1) a flexible framework relying on stochastic frame-averaging (SFA) to make any model E(3)-equivariant or invariant through data transformations. (2) FAENet: a simple, fast and expressive GNN, optimized for SFA, tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05577","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/2305.05577/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ONaLQd6LOlMVwoeqMQFeVt9mSnKLhV8Z3laDnM4Cunp4YPhDbmzR8ADsarCfW4EoOAQpqDImrvMfZYhD+LQrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:13:25.428962Z"},"content_sha256":"ad4fb0f049a7b0cf6d4e81deb2ae293052bd6908b62a1ce5b68ad0853be18dcd","schema_version":"1.0","event_id":"sha256:ad4fb0f049a7b0cf6d4e81deb2ae293052bd6908b62a1ce5b68ad0853be18dcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRI3YRNXYXNJJMLISAVBVXJR64/bundle.json","state_url":"https://pith.science/pith/JRI3YRNXYXNJJMLISAVBVXJR64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRI3YRNXYXNJJMLISAVBVXJR64/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":"2026-08-05T09:13:25Z","links":{"resolver":"https://pith.science/pith/JRI3YRNXYXNJJMLISAVBVXJR64","bundle":"https://pith.science/pith/JRI3YRNXYXNJJMLISAVBVXJR64/bundle.json","state":"https://pith.science/pith/JRI3YRNXYXNJJMLISAVBVXJR64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRI3YRNXYXNJJMLISAVBVXJR64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JRI3YRNXYXNJJMLISAVBVXJR64","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":"8bd233e22e3f5fc7abf6bdc62e51b52d9fa3ffa9b6b55e30268a6046458b06a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T21:48:31Z","title_canon_sha256":"7961b437c554aa58c6e28458c4e5fdfddd2c142783e9eb82d69a3a8c85b1ee6f"},"schema_version":"1.0","source":{"id":"2305.05577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05577","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05577v1","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05577","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"JRI3YRNXYXNJ","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"JRI3YRNXYXNJJMLI","created_at":"2026-07-05T06:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"JRI3YRNX","created_at":"2026-07-05T06:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:ad4fb0f049a7b0cf6d4e81deb2ae293052bd6908b62a1ce5b68ad0853be18dcd","target":"graph","created_at":"2026-07-05T06:08:36Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.05577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they enforce symmetries via the model architecture, which often reduces their expressivity, scalability and comprehensibility. In this paper, we introduce (1) a flexible framework relying on stochastic frame-averaging (SFA) to make any model E(3)-equivariant or invariant through data transformations. (2) FAENet: a simple, fast and expressive GNN, optimized for SFA, tha","authors_text":"Alexandre Duval, Alex Hernandez Garcia, David Rolnick, Fragkiskos D. Malliaros, Santiago Miret, Victor Schmidt, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T21:48:31Z","title":"FAENet: Frame Averaging Equivariant GNN for Materials Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05577","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:af4af41d42f67c9bea42f262ac6fd159b812c025ae47516eff9f624ea2734030","target":"record","created_at":"2026-07-05T06:08:36Z","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":"8bd233e22e3f5fc7abf6bdc62e51b52d9fa3ffa9b6b55e30268a6046458b06a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T21:48:31Z","title_canon_sha256":"7961b437c554aa58c6e28458c4e5fdfddd2c142783e9eb82d69a3a8c85b1ee6f"},"schema_version":"1.0","source":{"id":"2305.05577","kind":"arxiv","version":1}},"canonical_sha256":"4c51bc45b7c5da94b168902a1add31f733ea42b85c97536cf2d423bf1c94faa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c51bc45b7c5da94b168902a1add31f733ea42b85c97536cf2d423bf1c94faa0","first_computed_at":"2026-07-05T06:08:36.429946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:36.429946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U38tCBJhU6YubE/l6oJ33aGy+5/XM7ogVwymQ+VUMAOUqlMSAWBXYOeQiibrgEAXtp0up0tWotxpyWRASzq2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:36.430433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af4af41d42f67c9bea42f262ac6fd159b812c025ae47516eff9f624ea2734030","sha256:ad4fb0f049a7b0cf6d4e81deb2ae293052bd6908b62a1ce5b68ad0853be18dcd"],"state_sha256":"7da7efb3fa371ec6d5906830b94b53fd6235c66d614642538475cbe8623c45f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UaOjeJexyMWpDKWDc4S+1PZob1a/B48l08FnHGFBp0zHqyotneUVJkF2ZJy8I1qed28dWC+tLrih6bCewT50Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:13:25.436641Z","bundle_sha256":"7582e84ad6bbf52225fce6a563e9dd15d43fece33e269844397d0b1c775b2983"}}