{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5IU27TBRWIJFFD5XO4B2JQYEHO","short_pith_number":"pith:5IU27TBR","canonical_record":{"source":{"id":"1907.01992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:35:16Z","cross_cats_sorted":["cs.CV","physics.med-ph","stat.ML"],"title_canon_sha256":"83f83f2a2dc0c82fe2828706092c4da95456e3321d441d9f0191f6cb32e84978","abstract_canon_sha256":"661c7fef817aaebae5302b66592603af9632221b9bead8c5b38bab3fd93ecf90"},"schema_version":"1.0"},"canonical_sha256":"ea29afcc31b212528fb77703a4c3043b95aa61811d5da5ad2c646f3578b74980","source":{"kind":"arxiv","id":"1907.01992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01992","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01992v1","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01992","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"5IU27TBRWIJF","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"5IU27TBRWIJFFD5X","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"5IU27TBR","created_at":"2026-07-05T02:02:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5IU27TBRWIJFFD5XO4B2JQYEHO","target":"record","payload":{"canonical_record":{"source":{"id":"1907.01992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:35:16Z","cross_cats_sorted":["cs.CV","physics.med-ph","stat.ML"],"title_canon_sha256":"83f83f2a2dc0c82fe2828706092c4da95456e3321d441d9f0191f6cb32e84978","abstract_canon_sha256":"661c7fef817aaebae5302b66592603af9632221b9bead8c5b38bab3fd93ecf90"},"schema_version":"1.0"},"canonical_sha256":"ea29afcc31b212528fb77703a4c3043b95aa61811d5da5ad2c646f3578b74980","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:00.638937Z","signature_b64":"pvqbxyGlLybtISU0m1BDRENoOa4ynS9Wdtkv2OpGmxSKfgnZJHiExWbP6EUatW/BdtU7NW/G16Ij/fCv9C0sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea29afcc31b212528fb77703a4c3043b95aa61811d5da5ad2c646f3578b74980","last_reissued_at":"2026-07-05T02:02:00.638448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:00.638448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.01992","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":"2026-07-05T02:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tysgcyc7pYLStP9f4mnk7VLi8Skv/RgtrrbYKSo15YDHN8t34j9k03puRB6k0n1a5zWaGO/l9tFqQrZBego/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:27:34.251515Z"},"content_sha256":"efdc0d1aaa6bb45a6acf79fdd36cb1dd9f6c211158bd8cd9348acb88c34c45cf","schema_version":"1.0","event_id":"sha256:efdc0d1aaa6bb45a6acf79fdd36cb1dd9f6c211158bd8cd9348acb88c34c45cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5IU27TBRWIJFFD5XO4B2JQYEHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Known Operators reduces Maximum Training Error Bounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","physics.med-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas K. Maier, Bernhard Stimpel, Christopher Syben, Frank Schebesch, Lasse Kling, Leonid Mill, Mathis Hoffmann, Silke Christiansen, Tobias W\\\"urfl, Weilin Fu","submitted_at":"2019-07-03T15:35:16Z","abstract_excerpt":"We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient towards its inputs is suited for our framework. We derive a maximal error bound for deep nets that demonstrates that inclusion of prior knowledge results in its reduction. Furthermore, we also show experimentally that known operators reduce the number of free parameters. We apply this approach to various "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01992","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/1907.01992/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":"2026-07-05T02:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUXbdT7Ssg+dbn2UyGLW6fBKQ+1FGN4CyWSfjKnkBwz7hDfseRNwdq76+XyMjYwb1OtIRop3tuPAeET9nHNUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:27:34.252613Z"},"content_sha256":"ccf2f41446ea5bc45b6bb2d67dc054d5f0bf104975dd58fd05d81194c8c05fbd","schema_version":"1.0","event_id":"sha256:ccf2f41446ea5bc45b6bb2d67dc054d5f0bf104975dd58fd05d81194c8c05fbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IU27TBRWIJFFD5XO4B2JQYEHO/bundle.json","state_url":"https://pith.science/pith/5IU27TBRWIJFFD5XO4B2JQYEHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IU27TBRWIJFFD5XO4B2JQYEHO/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":"2026-08-20T01:27:34Z","links":{"resolver":"https://pith.science/pith/5IU27TBRWIJFFD5XO4B2JQYEHO","bundle":"https://pith.science/pith/5IU27TBRWIJFFD5XO4B2JQYEHO/bundle.json","state":"https://pith.science/pith/5IU27TBRWIJFFD5XO4B2JQYEHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IU27TBRWIJFFD5XO4B2JQYEHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5IU27TBRWIJFFD5XO4B2JQYEHO","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":"661c7fef817aaebae5302b66592603af9632221b9bead8c5b38bab3fd93ecf90","cross_cats_sorted":["cs.CV","physics.med-ph","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:35:16Z","title_canon_sha256":"83f83f2a2dc0c82fe2828706092c4da95456e3321d441d9f0191f6cb32e84978"},"schema_version":"1.0","source":{"id":"1907.01992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01992","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01992v1","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01992","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"5IU27TBRWIJF","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"5IU27TBRWIJFFD5X","created_at":"2026-07-05T02:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"5IU27TBR","created_at":"2026-07-05T02:02:00Z"}],"graph_snapshots":[{"event_id":"sha256:ccf2f41446ea5bc45b6bb2d67dc054d5f0bf104975dd58fd05d81194c8c05fbd","target":"graph","created_at":"2026-07-05T02:02:00Z","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/1907.01992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient towards its inputs is suited for our framework. We derive a maximal error bound for deep nets that demonstrates that inclusion of prior knowledge results in its reduction. Furthermore, we also show experimentally that known operators reduce the number of free parameters. We apply this approach to various ","authors_text":"Andreas K. Maier, Bernhard Stimpel, Christopher Syben, Frank Schebesch, Lasse Kling, Leonid Mill, Mathis Hoffmann, Silke Christiansen, Tobias W\\\"urfl, Weilin Fu","cross_cats":["cs.CV","physics.med-ph","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:35:16Z","title":"Learning with Known Operators reduces Maximum Training Error Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01992","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:efdc0d1aaa6bb45a6acf79fdd36cb1dd9f6c211158bd8cd9348acb88c34c45cf","target":"record","created_at":"2026-07-05T02:02:00Z","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":"661c7fef817aaebae5302b66592603af9632221b9bead8c5b38bab3fd93ecf90","cross_cats_sorted":["cs.CV","physics.med-ph","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T15:35:16Z","title_canon_sha256":"83f83f2a2dc0c82fe2828706092c4da95456e3321d441d9f0191f6cb32e84978"},"schema_version":"1.0","source":{"id":"1907.01992","kind":"arxiv","version":1}},"canonical_sha256":"ea29afcc31b212528fb77703a4c3043b95aa61811d5da5ad2c646f3578b74980","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea29afcc31b212528fb77703a4c3043b95aa61811d5da5ad2c646f3578b74980","first_computed_at":"2026-07-05T02:02:00.638448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:02:00.638448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pvqbxyGlLybtISU0m1BDRENoOa4ynS9Wdtkv2OpGmxSKfgnZJHiExWbP6EUatW/BdtU7NW/G16Ij/fCv9C0sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:02:00.638937Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.01992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efdc0d1aaa6bb45a6acf79fdd36cb1dd9f6c211158bd8cd9348acb88c34c45cf","sha256:ccf2f41446ea5bc45b6bb2d67dc054d5f0bf104975dd58fd05d81194c8c05fbd"],"state_sha256":"7f44c45de0c88b71461a7a3c14df4e9c466574685de64b09cffe84538f5f453d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CiOKEB9qojCu7RhUejhHuzGyyCEw5T2ZpNOVBGkE2KQwVzvGJaSGRsVB3odIrXzpT5rsDe6Bxac2cNEtO3g0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:27:34.260700Z","bundle_sha256":"87db726617ab65bfc3e65edd3c32f6394332f08404e5287a84dea70ea5f7c55d"}}