{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6TEZ6USTW6HYUU7QBGAT6D245M","short_pith_number":"pith:6TEZ6UST","canonical_record":{"source":{"id":"2505.22560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T16:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"b99fdcc88134ea7e74a958f3bc2dfa84588481fd3883abc4b8f0cc1d9cb83631","abstract_canon_sha256":"e5dfdc3f2518debae7bbb5f8ad48ab5b3a3b414c39397125598c6a5a77a4e321"},"schema_version":"1.0"},"canonical_sha256":"f4c99f5253b78f8a53f009813f0f5ceb0575b265e07fd4709e0ddab375a89251","source":{"kind":"arxiv","id":"2505.22560","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22560","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22560v1","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22560","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"6TEZ6USTW6HY","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"6TEZ6USTW6HYUU7Q","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"6TEZ6UST","created_at":"2026-07-05T11:11:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6TEZ6USTW6HYUU7QBGAT6D245M","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T16:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"b99fdcc88134ea7e74a958f3bc2dfa84588481fd3883abc4b8f0cc1d9cb83631","abstract_canon_sha256":"e5dfdc3f2518debae7bbb5f8ad48ab5b3a3b414c39397125598c6a5a77a4e321"},"schema_version":"1.0"},"canonical_sha256":"f4c99f5253b78f8a53f009813f0f5ceb0575b265e07fd4709e0ddab375a89251","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:26.742567Z","signature_b64":"47NRA/KecFhh0JYJavIH7V728NBaZb+ARgAPsUKb1GtwAqwCFGOFC+QqcaCro4nz+LT0ceCSPSdm/DgiRs5iAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4c99f5253b78f8a53f009813f0f5ceb0575b265e07fd4709e0ddab375a89251","last_reissued_at":"2026-07-05T11:11:26.742067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:26.742067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22560","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":"2026-07-05T11:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LGPJ8bDjYWjzXzOtcBK9K/BU4hen3D45ux0pm8qLMVklRMfuhkHqyEruhjratV1fxDXCf+fHPGja/h5mb4WjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:58:02.191864Z"},"content_sha256":"df7473b70dbf46a605469e9b926e15dacb951df980291765d4b733afa4a327fc","schema_version":"1.0","event_id":"sha256:df7473b70dbf46a605469e9b926e15dacb951df980291765d4b733afa4a327fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6TEZ6USTW6HYUU7QBGAT6D245M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Hyena Networks for Large-scale Equivariant Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Artem Moskalev, Junjie Xu, Mangal Prakash, Rui Liao, Tianyu Cui, Tommaso Mansi","submitted_at":"2025-05-28T16:38:35Z","abstract_excerpt":"Processing global geometric context while preserving equivariance is crucial when modeling biological, chemical, and physical systems. Yet, this is challenging due to the computational demands of equivariance and global context at scale. Standard methods such as equivariant self-attention suffer from quadratic complexity, while local methods such as distance-based message passing sacrifice global information. Inspired by the recent success of state-space and long-convolutional models, we introduce Geometric Hyena, the first equivariant long-convolutional model for geometric systems. Geometric "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22560","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/2505.22560/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":"2026-07-05T11:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGQQfMd9sqUgJB/j7QRxc5QxxDDFRZJf3SYmp/aUVI/B2NNNQYeCNCNXxmhqkqGf1iLMdh6I1h+9HhC/a8zBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:58:02.192488Z"},"content_sha256":"7954eb83e567b50ae93b703591409482e83176b6fca97511f7dc65ad251a9a85","schema_version":"1.0","event_id":"sha256:7954eb83e567b50ae93b703591409482e83176b6fca97511f7dc65ad251a9a85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TEZ6USTW6HYUU7QBGAT6D245M/bundle.json","state_url":"https://pith.science/pith/6TEZ6USTW6HYUU7QBGAT6D245M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TEZ6USTW6HYUU7QBGAT6D245M/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":"2026-08-06T18:58:02Z","links":{"resolver":"https://pith.science/pith/6TEZ6USTW6HYUU7QBGAT6D245M","bundle":"https://pith.science/pith/6TEZ6USTW6HYUU7QBGAT6D245M/bundle.json","state":"https://pith.science/pith/6TEZ6USTW6HYUU7QBGAT6D245M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TEZ6USTW6HYUU7QBGAT6D245M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6TEZ6USTW6HYUU7QBGAT6D245M","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":"e5dfdc3f2518debae7bbb5f8ad48ab5b3a3b414c39397125598c6a5a77a4e321","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T16:38:35Z","title_canon_sha256":"b99fdcc88134ea7e74a958f3bc2dfa84588481fd3883abc4b8f0cc1d9cb83631"},"schema_version":"1.0","source":{"id":"2505.22560","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22560","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22560v1","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22560","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"6TEZ6USTW6HY","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"6TEZ6USTW6HYUU7Q","created_at":"2026-07-05T11:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"6TEZ6UST","created_at":"2026-07-05T11:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:7954eb83e567b50ae93b703591409482e83176b6fca97511f7dc65ad251a9a85","target":"graph","created_at":"2026-07-05T11:11:26Z","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/2505.22560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Processing global geometric context while preserving equivariance is crucial when modeling biological, chemical, and physical systems. Yet, this is challenging due to the computational demands of equivariance and global context at scale. Standard methods such as equivariant self-attention suffer from quadratic complexity, while local methods such as distance-based message passing sacrifice global information. Inspired by the recent success of state-space and long-convolutional models, we introduce Geometric Hyena, the first equivariant long-convolutional model for geometric systems. Geometric ","authors_text":"Artem Moskalev, Junjie Xu, Mangal Prakash, Rui Liao, Tianyu Cui, Tommaso Mansi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T16:38:35Z","title":"Geometric Hyena Networks for Large-scale Equivariant Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22560","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:df7473b70dbf46a605469e9b926e15dacb951df980291765d4b733afa4a327fc","target":"record","created_at":"2026-07-05T11:11:26Z","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":"e5dfdc3f2518debae7bbb5f8ad48ab5b3a3b414c39397125598c6a5a77a4e321","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T16:38:35Z","title_canon_sha256":"b99fdcc88134ea7e74a958f3bc2dfa84588481fd3883abc4b8f0cc1d9cb83631"},"schema_version":"1.0","source":{"id":"2505.22560","kind":"arxiv","version":1}},"canonical_sha256":"f4c99f5253b78f8a53f009813f0f5ceb0575b265e07fd4709e0ddab375a89251","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4c99f5253b78f8a53f009813f0f5ceb0575b265e07fd4709e0ddab375a89251","first_computed_at":"2026-07-05T11:11:26.742067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:26.742067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"47NRA/KecFhh0JYJavIH7V728NBaZb+ARgAPsUKb1GtwAqwCFGOFC+QqcaCro4nz+LT0ceCSPSdm/DgiRs5iAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:26.742567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22560","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df7473b70dbf46a605469e9b926e15dacb951df980291765d4b733afa4a327fc","sha256:7954eb83e567b50ae93b703591409482e83176b6fca97511f7dc65ad251a9a85"],"state_sha256":"bb6cc1b99d3defb5227127dbbdcf72e7de753e973287f7f2cce8746c2cd5f669"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e2YMjSb3/8xgoOupze+kRNglRg8u1+wnS1S/3WnkaJUiAcrKbiOVV3v5yXWcM0DvqtMRAWYSrIn+lfgzOMNIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:58:02.196972Z","bundle_sha256":"6579c227692290a15cf1bd11807106980ff82f73b192cace62c776a348b038e9"}}