{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W56WAMFRURJWHIVZOCJT3U5JXB","short_pith_number":"pith:W56WAMFR","canonical_record":{"source":{"id":"2410.04209","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T15:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"cd233a3f79e457ecb46329887ea19e65dc1290e409e13a33c93028f7a7770651","abstract_canon_sha256":"b1473ae55494fe42c8a6a434e5ed09edda062c32564eb87d8bc189542749bc0e"},"schema_version":"1.0"},"canonical_sha256":"b77d6030b1a45363a2b970933dd3a9b843db338f54e3159cfc622feb8b6b89fd","source":{"kind":"arxiv","id":"2410.04209","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04209","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04209v2","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04209","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"pith_short_12","alias_value":"W56WAMFRURJW","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"pith_short_16","alias_value":"W56WAMFRURJWHIVZ","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"pith_short_8","alias_value":"W56WAMFR","created_at":"2026-07-05T10:26:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W56WAMFRURJWHIVZOCJT3U5JXB","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04209","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T15:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"cd233a3f79e457ecb46329887ea19e65dc1290e409e13a33c93028f7a7770651","abstract_canon_sha256":"b1473ae55494fe42c8a6a434e5ed09edda062c32564eb87d8bc189542749bc0e"},"schema_version":"1.0"},"canonical_sha256":"b77d6030b1a45363a2b970933dd3a9b843db338f54e3159cfc622feb8b6b89fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:08.460666Z","signature_b64":"uN5AyBjyQ/wjVemd543HTusmgreu6of3AS2zZqOyDQ40pQh8QVRChhj/LAKf6GjUc+m6LKgKMVbsgs+x/kY3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b77d6030b1a45363a2b970933dd3a9b843db338f54e3159cfc622feb8b6b89fd","last_reissued_at":"2026-07-05T10:26:08.459797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:08.459797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04209","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":"2026-07-05T10:26:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKBkcMy14LfT9RD/AoDannl5RComRi3rE7/GaRsuo7IkvhexNM8h32nv59LVhz/jX1zl/ScTuRwai6+sYjnJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:11:39.402826Z"},"content_sha256":"42b6860a909fd85afab665f863423a14e8a335ce2a713a4608c277415d68e78a","schema_version":"1.0","event_id":"sha256:42b6860a909fd85afab665f863423a14e8a335ce2a713a4608c277415d68e78a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W56WAMFRURJWHIVZOCJT3U5JXB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Equivariant Neural Functional Networks for Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An Nguyen The, Duy-Tung Pham, Minh-Khoi Nguyen-Nhat, Tan Minh Nguyen, Thanh Tran, Thieu N. Vo, Tho Tran Huu, Viet-Hoang Tran","submitted_at":"2024-10-05T15:56:57Z","abstract_excerpt":"This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or sparsity patterns of a deep neural network (DNN) as input data and have proven valuable for tasks such as learnable optimizers, implicit data representations, and weight editing. While NFN have been extensively developed for MLP and CNN, no prior work has addressed their design for transformers, despite the importance of transformers in modern deep learning. This paper aims to address this gap by providing a systematic stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04209","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/2410.04209/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":"2026-07-05T10:26:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9e8EBIgtSzci1oYl6UiMYOidA1vaGXPx1Io+WGyRzHWy30/UWfGg+4Qj1SrcIn9Z2A0p7S+cuKTKfVQXogTpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:11:39.403361Z"},"content_sha256":"8dbd31d29c98c031c7bbcb40a577fa984cc35cc74d5a9505f14ee4697e902b20","schema_version":"1.0","event_id":"sha256:8dbd31d29c98c031c7bbcb40a577fa984cc35cc74d5a9505f14ee4697e902b20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W56WAMFRURJWHIVZOCJT3U5JXB/bundle.json","state_url":"https://pith.science/pith/W56WAMFRURJWHIVZOCJT3U5JXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W56WAMFRURJWHIVZOCJT3U5JXB/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":"2026-07-31T14:11:39Z","links":{"resolver":"https://pith.science/pith/W56WAMFRURJWHIVZOCJT3U5JXB","bundle":"https://pith.science/pith/W56WAMFRURJWHIVZOCJT3U5JXB/bundle.json","state":"https://pith.science/pith/W56WAMFRURJWHIVZOCJT3U5JXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W56WAMFRURJWHIVZOCJT3U5JXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W56WAMFRURJWHIVZOCJT3U5JXB","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":"b1473ae55494fe42c8a6a434e5ed09edda062c32564eb87d8bc189542749bc0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T15:56:57Z","title_canon_sha256":"cd233a3f79e457ecb46329887ea19e65dc1290e409e13a33c93028f7a7770651"},"schema_version":"1.0","source":{"id":"2410.04209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04209","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04209v2","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04209","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"pith_short_12","alias_value":"W56WAMFRURJW","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"pith_short_16","alias_value":"W56WAMFRURJWHIVZ","created_at":"2026-07-05T10:26:08Z"},{"alias_kind":"pith_short_8","alias_value":"W56WAMFR","created_at":"2026-07-05T10:26:08Z"}],"graph_snapshots":[{"event_id":"sha256:8dbd31d29c98c031c7bbcb40a577fa984cc35cc74d5a9505f14ee4697e902b20","target":"graph","created_at":"2026-07-05T10:26:08Z","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/2410.04209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper systematically explores neural functional networks (NFN) for transformer architectures. NFN are specialized neural networks that treat the weights, gradients, or sparsity patterns of a deep neural network (DNN) as input data and have proven valuable for tasks such as learnable optimizers, implicit data representations, and weight editing. While NFN have been extensively developed for MLP and CNN, no prior work has addressed their design for transformers, despite the importance of transformers in modern deep learning. This paper aims to address this gap by providing a systematic stud","authors_text":"An Nguyen The, Duy-Tung Pham, Minh-Khoi Nguyen-Nhat, Tan Minh Nguyen, Thanh Tran, Thieu N. Vo, Tho Tran Huu, Viet-Hoang Tran","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T15:56:57Z","title":"Equivariant Neural Functional Networks for Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04209","kind":"arxiv","version":2},"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":"sha256:42b6860a909fd85afab665f863423a14e8a335ce2a713a4608c277415d68e78a","target":"record","created_at":"2026-07-05T10:26:08Z","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":"b1473ae55494fe42c8a6a434e5ed09edda062c32564eb87d8bc189542749bc0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-05T15:56:57Z","title_canon_sha256":"cd233a3f79e457ecb46329887ea19e65dc1290e409e13a33c93028f7a7770651"},"schema_version":"1.0","source":{"id":"2410.04209","kind":"arxiv","version":2}},"canonical_sha256":"b77d6030b1a45363a2b970933dd3a9b843db338f54e3159cfc622feb8b6b89fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b77d6030b1a45363a2b970933dd3a9b843db338f54e3159cfc622feb8b6b89fd","first_computed_at":"2026-07-05T10:26:08.459797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:08.459797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uN5AyBjyQ/wjVemd543HTusmgreu6of3AS2zZqOyDQ40pQh8QVRChhj/LAKf6GjUc+m6LKgKMVbsgs+x/kY3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:08.460666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42b6860a909fd85afab665f863423a14e8a335ce2a713a4608c277415d68e78a","sha256:8dbd31d29c98c031c7bbcb40a577fa984cc35cc74d5a9505f14ee4697e902b20"],"state_sha256":"f476b00abdfd04d14a8df0a8c069fee55c6b94a477ef0f113f9290604250789e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PDMU3gn96joVzOIiPf2r7ISPI8Okm33RfQi0KdkKDgu9OOleHe2r4EHW4wEAwnhrn8zWLeXpwXxCPviT2Ch0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:11:39.410190Z","bundle_sha256":"fff41c9748f80f1f8d20ad32b89303681ca804e5e9941ec1bcae061349f74e62"}}