{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3GTO2PNJXSORONE76XI2MVKHNX","short_pith_number":"pith:3GTO2PNJ","canonical_record":{"source":{"id":"2601.05028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T15:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"34551ca48c97ea4b0852eb2ad9b53c4ee53643cc37c354fbbbfda93a8163a848","abstract_canon_sha256":"455aa3446f2d36d4830cefa21bc8f938624c9bde88af6eeb834d5f58e3a46fdf"},"schema_version":"1.0"},"canonical_sha256":"d9a6ed3da9bc9d17349ff5d1a655476df528c96ce8a8b906f32a6cf87bb7451a","source":{"kind":"arxiv","id":"2601.05028","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.05028","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.05028v2","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05028","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"3GTO2PNJXSOR","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"3GTO2PNJXSORONE7","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"3GTO2PNJ","created_at":"2026-05-27T01:05:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3GTO2PNJXSORONE76XI2MVKHNX","target":"record","payload":{"canonical_record":{"source":{"id":"2601.05028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T15:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"34551ca48c97ea4b0852eb2ad9b53c4ee53643cc37c354fbbbfda93a8163a848","abstract_canon_sha256":"455aa3446f2d36d4830cefa21bc8f938624c9bde88af6eeb834d5f58e3a46fdf"},"schema_version":"1.0"},"canonical_sha256":"d9a6ed3da9bc9d17349ff5d1a655476df528c96ce8a8b906f32a6cf87bb7451a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:42.208547Z","signature_b64":"puQAtzWkdfvAhO+kvOW4nm+OMQkaifIP+QYRJwdtLXpi73rYxwBzsYCaSx9QRV5vQAM0BgKxF9OeC/MZb5oaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a6ed3da9bc9d17349ff5d1a655476df528c96ce8a8b906f32a6cf87bb7451a","last_reissued_at":"2026-05-27T01:05:42.207941Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:42.207941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.05028","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":"2026-05-27T01:05:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWTbR9EQ34fc+a1CQOyKHcIjGSvpWZ1VbhFlj5sQjaCGHTmsOme5Ee/XR8+qlPOn2sr1zL/c6IMhKusR8OvNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:32:05.480396Z"},"content_sha256":"ee472cfe4de77daa2cd10ba6427cddef8ed9fad955f206fdcfa256e47f9e9d00","schema_version":"1.0","event_id":"sha256:ee472cfe4de77daa2cd10ba6427cddef8ed9fad955f206fdcfa256e47f9e9d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3GTO2PNJXSORONE76XI2MVKHNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Equivariance via Projection-based Regularisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jan St\\\"uhmer, Torben Berndt","submitted_at":"2026-01-08T15:35:42Z","abstract_excerpt":"Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant models have regained attention, due to their better runtime performance and imperfect symmetries that might arise in real-world applications. This has motivated the development of approximately equivariant models that strike a middle ground between respecting symmetries and fitting the data distribution. Existing approaches in this field usually apply sample-based regularisers which depend on data augmentation at training time, incurring a high sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05028","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/2601.05028/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":"2026-05-27T01:05:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ip+O7BT+z7VWerC2v0OqkJLsxHNVi43nEvk6Q9I4TCWdTqtgWt98iVJ/0WoZGbjzx/La+yydw3oHUcd99nleAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:32:05.480854Z"},"content_sha256":"c8bbc709d44b8fdd3bc3ae137463fd022764cbf2412eb350616b3f1e48e8dbaa","schema_version":"1.0","event_id":"sha256:c8bbc709d44b8fdd3bc3ae137463fd022764cbf2412eb350616b3f1e48e8dbaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GTO2PNJXSORONE76XI2MVKHNX/bundle.json","state_url":"https://pith.science/pith/3GTO2PNJXSORONE76XI2MVKHNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GTO2PNJXSORONE76XI2MVKHNX/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":"2026-06-05T18:32:05Z","links":{"resolver":"https://pith.science/pith/3GTO2PNJXSORONE76XI2MVKHNX","bundle":"https://pith.science/pith/3GTO2PNJXSORONE76XI2MVKHNX/bundle.json","state":"https://pith.science/pith/3GTO2PNJXSORONE76XI2MVKHNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GTO2PNJXSORONE76XI2MVKHNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3GTO2PNJXSORONE76XI2MVKHNX","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":"455aa3446f2d36d4830cefa21bc8f938624c9bde88af6eeb834d5f58e3a46fdf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T15:35:42Z","title_canon_sha256":"34551ca48c97ea4b0852eb2ad9b53c4ee53643cc37c354fbbbfda93a8163a848"},"schema_version":"1.0","source":{"id":"2601.05028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.05028","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.05028v2","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05028","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"3GTO2PNJXSOR","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"3GTO2PNJXSORONE7","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"3GTO2PNJ","created_at":"2026-05-27T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:c8bbc709d44b8fdd3bc3ae137463fd022764cbf2412eb350616b3f1e48e8dbaa","target":"graph","created_at":"2026-05-27T01:05:42Z","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/2601.05028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Equivariance is a powerful inductive bias in neural networks, improving generalisation and physical consistency. Recently, however, non-equivariant models have regained attention, due to their better runtime performance and imperfect symmetries that might arise in real-world applications. This has motivated the development of approximately equivariant models that strike a middle ground between respecting symmetries and fitting the data distribution. Existing approaches in this field usually apply sample-based regularisers which depend on data augmentation at training time, incurring a high sam","authors_text":"Jan St\\\"uhmer, Torben Berndt","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T15:35:42Z","title":"Approximate Equivariance via Projection-based Regularisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05028","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:ee472cfe4de77daa2cd10ba6427cddef8ed9fad955f206fdcfa256e47f9e9d00","target":"record","created_at":"2026-05-27T01:05:42Z","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":"455aa3446f2d36d4830cefa21bc8f938624c9bde88af6eeb834d5f58e3a46fdf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T15:35:42Z","title_canon_sha256":"34551ca48c97ea4b0852eb2ad9b53c4ee53643cc37c354fbbbfda93a8163a848"},"schema_version":"1.0","source":{"id":"2601.05028","kind":"arxiv","version":2}},"canonical_sha256":"d9a6ed3da9bc9d17349ff5d1a655476df528c96ce8a8b906f32a6cf87bb7451a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9a6ed3da9bc9d17349ff5d1a655476df528c96ce8a8b906f32a6cf87bb7451a","first_computed_at":"2026-05-27T01:05:42.207941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:42.207941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"puQAtzWkdfvAhO+kvOW4nm+OMQkaifIP+QYRJwdtLXpi73rYxwBzsYCaSx9QRV5vQAM0BgKxF9OeC/MZb5oaBg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:42.208547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.05028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee472cfe4de77daa2cd10ba6427cddef8ed9fad955f206fdcfa256e47f9e9d00","sha256:c8bbc709d44b8fdd3bc3ae137463fd022764cbf2412eb350616b3f1e48e8dbaa"],"state_sha256":"57ebd9fa257512e12bb79c395bfe8c45a4ae249e826336fd476e7ec00795f383"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bi4hxgoL50pPwaUjyehi1ShyBGFP/NgFYJEOdIvQ/WX655acyplMe8rCIfEggUaP/D2a2kFcfrEWR+dGBIAYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T18:32:05.483141Z","bundle_sha256":"5055264d4dadfc92f5a60035ecf6682fd1eb46008371e0c57af0c4b23d5f96a7"}}