{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F5B5SJGY4VN33FBMB5PU3THMHY","short_pith_number":"pith:F5B5SJGY","canonical_record":{"source":{"id":"2606.06724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"212734591ecf47c29aac8e91a3852e34c098020797fa3233eba019e4056b4668","abstract_canon_sha256":"bf0eedf048aaf95c71ca376130a2590333d7c7d4754a2f96b6906385ab0c38ae"},"schema_version":"1.0"},"canonical_sha256":"2f43d924d8e55bbd942c0f5f4dccec3e22cb127324fba9a5e5f9db042b4f7796","source":{"kind":"arxiv","id":"2606.06724","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06724","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06724v1","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06724","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"F5B5SJGY4VN3","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"F5B5SJGY4VN33FBM","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"F5B5SJGY","created_at":"2026-06-08T01:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F5B5SJGY4VN33FBMB5PU3THMHY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"212734591ecf47c29aac8e91a3852e34c098020797fa3233eba019e4056b4668","abstract_canon_sha256":"bf0eedf048aaf95c71ca376130a2590333d7c7d4754a2f96b6906385ab0c38ae"},"schema_version":"1.0"},"canonical_sha256":"2f43d924d8e55bbd942c0f5f4dccec3e22cb127324fba9a5e5f9db042b4f7796","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:24.709071Z","signature_b64":"L/E6mrPAYvifGUn10DLquXwio4mCdwGhk9+k43teE/zV1zAi3Cdc8Wif3vxZ1+W1ytd44ksEEeSaJyCYkAhrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f43d924d8e55bbd942c0f5f4dccec3e22cb127324fba9a5e5f9db042b4f7796","last_reissued_at":"2026-06-08T01:04:24.708249Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:24.708249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06724","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":"2026-06-08T01:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ez7XqoVS/o+q42pee37JAIgKm9ey2vczOIIcthIao0WL1WmA1Bwt0TZCjJ2jdgr1sQT2iA4J9I6pLyMv+99Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:54:42.954876Z"},"content_sha256":"654f1ab3dcfe4ae618c33024accd7aa28dd6eed24faff5af480981ff0a1e5f2c","schema_version":"1.0","event_id":"sha256:654f1ab3dcfe4ae618c33024accd7aa28dd6eed24faff5af480981ff0a1e5f2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F5B5SJGY4VN33FBMB5PU3THMHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthics: Synthetic Physics-like Datasets for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jari Veps\\\"al\\\"ainen","submitted_at":"2026-06-04T21:20:08Z","abstract_excerpt":"Representative data is fundamental in machine learning, as limited data hinders generalisation. Collecting sufficient real-world samples is often infeasible. Synthetic data generation offers a practical solution, but only if the generated data faithfully reflects the structure of real observations. In this paper, a method for generating synthetic regression datasets that structurally resemble physics equations from a given equation corpus is presented. The approach uses a Bayesian Probabilistic Context-Free Grammar to capture the underlying algebraic structure of the corpus, from which novel e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06724","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/2606.06724/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":"2026-06-08T01:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0fkGO+4he9SWz4QrIiLjHI3v+jkp+LmZ+C/nK69q4cDlVpHMxFhFi9IhvCJd6DAwqiI078PR3fgZkpyCi9wMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:54:42.955244Z"},"content_sha256":"af66d8280f59c2a755486741947366c4ace32f3a149115dde153039d4d9e7415","schema_version":"1.0","event_id":"sha256:af66d8280f59c2a755486741947366c4ace32f3a149115dde153039d4d9e7415"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5B5SJGY4VN33FBMB5PU3THMHY/bundle.json","state_url":"https://pith.science/pith/F5B5SJGY4VN33FBMB5PU3THMHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5B5SJGY4VN33FBMB5PU3THMHY/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":"2026-06-28T17:54:42Z","links":{"resolver":"https://pith.science/pith/F5B5SJGY4VN33FBMB5PU3THMHY","bundle":"https://pith.science/pith/F5B5SJGY4VN33FBMB5PU3THMHY/bundle.json","state":"https://pith.science/pith/F5B5SJGY4VN33FBMB5PU3THMHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5B5SJGY4VN33FBMB5PU3THMHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F5B5SJGY4VN33FBMB5PU3THMHY","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":"bf0eedf048aaf95c71ca376130a2590333d7c7d4754a2f96b6906385ab0c38ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:20:08Z","title_canon_sha256":"212734591ecf47c29aac8e91a3852e34c098020797fa3233eba019e4056b4668"},"schema_version":"1.0","source":{"id":"2606.06724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06724","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06724v1","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06724","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"F5B5SJGY4VN3","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"F5B5SJGY4VN33FBM","created_at":"2026-06-08T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"F5B5SJGY","created_at":"2026-06-08T01:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:af66d8280f59c2a755486741947366c4ace32f3a149115dde153039d4d9e7415","target":"graph","created_at":"2026-06-08T01:04:24Z","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/2606.06724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representative data is fundamental in machine learning, as limited data hinders generalisation. Collecting sufficient real-world samples is often infeasible. Synthetic data generation offers a practical solution, but only if the generated data faithfully reflects the structure of real observations. In this paper, a method for generating synthetic regression datasets that structurally resemble physics equations from a given equation corpus is presented. The approach uses a Bayesian Probabilistic Context-Free Grammar to capture the underlying algebraic structure of the corpus, from which novel e","authors_text":"Jari Veps\\\"al\\\"ainen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:20:08Z","title":"Synthics: Synthetic Physics-like Datasets for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06724","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":"sha256:654f1ab3dcfe4ae618c33024accd7aa28dd6eed24faff5af480981ff0a1e5f2c","target":"record","created_at":"2026-06-08T01:04:24Z","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":"bf0eedf048aaf95c71ca376130a2590333d7c7d4754a2f96b6906385ab0c38ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T21:20:08Z","title_canon_sha256":"212734591ecf47c29aac8e91a3852e34c098020797fa3233eba019e4056b4668"},"schema_version":"1.0","source":{"id":"2606.06724","kind":"arxiv","version":1}},"canonical_sha256":"2f43d924d8e55bbd942c0f5f4dccec3e22cb127324fba9a5e5f9db042b4f7796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f43d924d8e55bbd942c0f5f4dccec3e22cb127324fba9a5e5f9db042b4f7796","first_computed_at":"2026-06-08T01:04:24.708249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:24.708249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L/E6mrPAYvifGUn10DLquXwio4mCdwGhk9+k43teE/zV1zAi3Cdc8Wif3vxZ1+W1ytd44ksEEeSaJyCYkAhrDw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:24.709071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:654f1ab3dcfe4ae618c33024accd7aa28dd6eed24faff5af480981ff0a1e5f2c","sha256:af66d8280f59c2a755486741947366c4ace32f3a149115dde153039d4d9e7415"],"state_sha256":"47889256f5a5882a264f6fecb32bf4427775f7918f34fde3758b17fbc148ef16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlMOUSUM/onfia8Kpr0sdWspMM/o+Yi5GXgGoPY0bMJLN50IACuIguBkku/QijIMAr8F9wl+3voptSDwN7VCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T17:54:42.957180Z","bundle_sha256":"7fcbe11e9412d120bec7ae9cf90c63ce711a6e94bcff6a455c0c51ae2d9e5a61"}}