{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GAJN6ORTQAYIWGQ3GZCGRJLVFB","short_pith_number":"pith:GAJN6ORT","canonical_record":{"source":{"id":"2605.14318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:29:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f25af40e7fe53274da9371005236413857cb8d01a8bc408af2f1d63496f17bc4","abstract_canon_sha256":"30d0f12864b092d66fb5de38bea33d356900c32d63c40a1423cf1aa3d545ace8"},"schema_version":"1.0"},"canonical_sha256":"3012df3a3380308b1a1b364468a575285460cb28f23cdc903e15e090641a0386","source":{"kind":"arxiv","id":"2605.14318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14318","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14318v1","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14318","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"GAJN6ORTQAYI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GAJN6ORTQAYIWGQ3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GAJN6ORT","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GAJN6ORTQAYIWGQ3GZCGRJLVFB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:29:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f25af40e7fe53274da9371005236413857cb8d01a8bc408af2f1d63496f17bc4","abstract_canon_sha256":"30d0f12864b092d66fb5de38bea33d356900c32d63c40a1423cf1aa3d545ace8"},"schema_version":"1.0"},"canonical_sha256":"3012df3a3380308b1a1b364468a575285460cb28f23cdc903e15e090641a0386","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:09.876368Z","signature_b64":"+jakrHd8WAuiYSb84Tm353xwyLAPrbWyDsAH5BXyfEuAZmqcjjbfSH/xKshVzITCmo5R2Eo1oDJjkLU2khRvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3012df3a3380308b1a1b364468a575285460cb28f23cdc903e15e090641a0386","last_reissued_at":"2026-05-17T23:39:09.875853Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:09.875853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14318","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":"2026-05-17T23:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VeKm1jpk3GRbv1c3E/wby9xyy1tb9B2Hkm4dUaXOpyVu8Zq52KcNLHIFAK235Pks2G6DR2AJfqwZVed+vH/+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T01:21:42.489969Z"},"content_sha256":"59aceaf57e51ed4579091503e7b782108990fb93c6dff7badd639d60f19b9c92","schema_version":"1.0","event_id":"sha256:59aceaf57e51ed4579091503e7b782108990fb93c6dff7badd639d60f19b9c92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GAJN6ORTQAYIWGQ3GZCGRJLVFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Feature Segmentation for Interpretable Predictive Maintenance in Complex Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Semantic feature segmentation isolates a canonical group of monitoring signals that carries the dominant information for anticipating faults.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandro Costa, Emilio Mastriani, Federico Incardona, Kevin Munari, Sebastiano Spinello","submitted_at":"2026-05-14T03:29:37Z","abstract_excerpt":"Predictive maintenance in complex systems is often complicated by the heterogeneity and redundancy of monitored variables,which can obscure fault-relevant information and reduce model interpretability. This work proposes a semantic feature segmentation framework that decomposes the monitored feature space into a canonical component,expected to retain the dominant predictive information, and a residual component containing structurally peripheral signals. The segmentation is defined through domain informed criteria and sets up monitoring variables into functional groups reflecting operational m"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the canonical space consistently achieves lower predictive risk than the residual space across multiple temporal configurations, indicating that the semantic segmentation concentrates the most relevant information for fault anticipation","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the domain-informed criteria used to define functional groups and separate canonical from residual components accurately isolate the dominant predictive information without bias from the grouping choices themselves.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Semantic segmentation decomposes monitoring features into canonical and residual components that concentrate fault-predictive information while preserving operational meaning in predictive maintenance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Semantic feature segmentation isolates a canonical group of monitoring signals that carries the dominant information for anticipating faults.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"761ac47f2776ea8a45b741bdde9e662c28ae66ff219351a0f5899270092d53b7"},"source":{"id":"2605.14318","kind":"arxiv","version":1},"verdict":{"id":"faaa7e2c-d3cf-44ec-8485-928a9288855d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:25:55.725678Z","strongest_claim":"the canonical space consistently achieves lower predictive risk than the residual space across multiple temporal configurations, indicating that the semantic segmentation concentrates the most relevant information for fault anticipation","one_line_summary":"Semantic segmentation decomposes monitoring features into canonical and residual components that concentrate fault-predictive information while preserving operational meaning in predictive maintenance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the domain-informed criteria used to define functional groups and separate canonical from residual components accurately isolate the dominant predictive information without bias from the grouping choices themselves.","pith_extraction_headline":"Semantic feature segmentation isolates a canonical group of monitoring signals that carries the dominant information for anticipating faults."},"references":{"count":29,"sample":[{"doi":"10.1016/j.ress.2023.109306","year":2023,"title":"Reliability Engineering & System Safety , author =","work_id":"05373bdb-fa68-4247-9bfe-ef600aa0eb0e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/asmb.70084","year":2026,"title":"Applied Stochastic Models in Business and Industry , author =","work_id":"20b01e1d-00e2-4309-9d2d-bcb25f32b3bd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.eswa.2025.127675","year":2025,"title":"2025 , issn =","work_id":"fcef7efa-dfda-4f77-b5e4-68123b4b3019","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3390/s25010137","year":2024,"title":"Sensors , author =","work_id":"0e095c68-35a0-4268-a7a5-b5db91d77b41","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.knosys.2025.113940","year":2025,"title":"Journal of Differential Equations454, 113940 (2026) https://doi.org/10.1016/j.jde.2025.113940","work_id":"6368b0ec-72b9-4b9b-9898-bf3124757fb3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"a10d1222564a13ad92496a558f247a91ee68d072201650a4c1ff363d68ce8aba","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7c2f29b4d91ce0ada919c8e7a1205e3d4255867dddcbb2961a274bec38a18338"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"faaa7e2c-d3cf-44ec-8485-928a9288855d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O8TvjrBgHweGrgb1lTZeRrrN3JNcQTyGXvy14D0z+sax2gOXp/M1VwVTAGVQKFiJNf/rJivmWEQDQ9tkbjdZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T01:21:42.490509Z"},"content_sha256":"094a1a12fda92bb297e5761d675c2ef3188e88741cb84ac209ad4b5e4910c287","schema_version":"1.0","event_id":"sha256:094a1a12fda92bb297e5761d675c2ef3188e88741cb84ac209ad4b5e4910c287"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB/bundle.json","state_url":"https://pith.science/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB/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":"2026-06-06T01:21:42Z","links":{"resolver":"https://pith.science/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB","bundle":"https://pith.science/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB/bundle.json","state":"https://pith.science/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAJN6ORTQAYIWGQ3GZCGRJLVFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GAJN6ORTQAYIWGQ3GZCGRJLVFB","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":"30d0f12864b092d66fb5de38bea33d356900c32d63c40a1423cf1aa3d545ace8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:29:37Z","title_canon_sha256":"f25af40e7fe53274da9371005236413857cb8d01a8bc408af2f1d63496f17bc4"},"schema_version":"1.0","source":{"id":"2605.14318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14318","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14318v1","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14318","created_at":"2026-05-17T23:39:09Z"},{"alias_kind":"pith_short_12","alias_value":"GAJN6ORTQAYI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"GAJN6ORTQAYIWGQ3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"GAJN6ORT","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:094a1a12fda92bb297e5761d675c2ef3188e88741cb84ac209ad4b5e4910c287","target":"graph","created_at":"2026-05-17T23:39:09Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"the canonical space consistently achieves lower predictive risk than the residual space across multiple temporal configurations, indicating that the semantic segmentation concentrates the most relevant information for fault anticipation"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the domain-informed criteria used to define functional groups and separate canonical from residual components accurately isolate the dominant predictive information without bias from the grouping choices themselves."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Semantic segmentation decomposes monitoring features into canonical and residual components that concentrate fault-predictive information while preserving operational meaning in predictive maintenance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Semantic feature segmentation isolates a canonical group of monitoring signals that carries the dominant information for anticipating faults."}],"snapshot_sha256":"761ac47f2776ea8a45b741bdde9e662c28ae66ff219351a0f5899270092d53b7"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7c2f29b4d91ce0ada919c8e7a1205e3d4255867dddcbb2961a274bec38a18338"},"paper":{"abstract_excerpt":"Predictive maintenance in complex systems is often complicated by the heterogeneity and redundancy of monitored variables,which can obscure fault-relevant information and reduce model interpretability. This work proposes a semantic feature segmentation framework that decomposes the monitored feature space into a canonical component,expected to retain the dominant predictive information, and a residual component containing structurally peripheral signals. The segmentation is defined through domain informed criteria and sets up monitoring variables into functional groups reflecting operational m","authors_text":"Alessandro Costa, Emilio Mastriani, Federico Incardona, Kevin Munari, Sebastiano Spinello","cross_cats":["cs.LG"],"headline":"Semantic feature segmentation isolates a canonical group of monitoring signals that carries the dominant information for anticipating faults.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:29:37Z","title":"Semantic Feature Segmentation for Interpretable Predictive Maintenance in Complex Systems"},"references":{"count":29,"internal_anchors":1,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"10.1016/j.ress.2023.109306","is_internal_anchor":false,"ref_index":1,"title":"Reliability Engineering & System Safety , author =","work_id":"05373bdb-fa68-4247-9bfe-ef600aa0eb0e","year":2023},{"cited_arxiv_id":"","doi":"10.1002/asmb.70084","is_internal_anchor":false,"ref_index":2,"title":"Applied Stochastic Models in Business and Industry , author =","work_id":"20b01e1d-00e2-4309-9d2d-bcb25f32b3bd","year":2026},{"cited_arxiv_id":"","doi":"10.1016/j.eswa.2025.127675","is_internal_anchor":false,"ref_index":3,"title":"2025 , issn =","work_id":"fcef7efa-dfda-4f77-b5e4-68123b4b3019","year":2025},{"cited_arxiv_id":"","doi":"10.3390/s25010137","is_internal_anchor":false,"ref_index":4,"title":"Sensors , author =","work_id":"0e095c68-35a0-4268-a7a5-b5db91d77b41","year":2024},{"cited_arxiv_id":"","doi":"10.1016/j.knosys.2025.113940","is_internal_anchor":false,"ref_index":5,"title":"Journal of Differential Equations454, 113940 (2026) https://doi.org/10.1016/j.jde.2025.113940","work_id":"6368b0ec-72b9-4b9b-9898-bf3124757fb3","year":2025}],"snapshot_sha256":"a10d1222564a13ad92496a558f247a91ee68d072201650a4c1ff363d68ce8aba"},"source":{"id":"2605.14318","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:25:55.725678Z","id":"faaa7e2c-d3cf-44ec-8485-928a9288855d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Semantic segmentation decomposes monitoring features into canonical and residual components that concentrate fault-predictive information while preserving operational meaning in predictive maintenance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Semantic feature segmentation isolates a canonical group of monitoring signals that carries the dominant information for anticipating faults.","strongest_claim":"the canonical space consistently achieves lower predictive risk than the residual space across multiple temporal configurations, indicating that the semantic segmentation concentrates the most relevant information for fault anticipation","weakest_assumption":"That the domain-informed criteria used to define functional groups and separate canonical from residual components accurately isolate the dominant predictive information without bias from the grouping choices themselves."}},"verdict_id":"faaa7e2c-d3cf-44ec-8485-928a9288855d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59aceaf57e51ed4579091503e7b782108990fb93c6dff7badd639d60f19b9c92","target":"record","created_at":"2026-05-17T23:39:09Z","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":"30d0f12864b092d66fb5de38bea33d356900c32d63c40a1423cf1aa3d545ace8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T03:29:37Z","title_canon_sha256":"f25af40e7fe53274da9371005236413857cb8d01a8bc408af2f1d63496f17bc4"},"schema_version":"1.0","source":{"id":"2605.14318","kind":"arxiv","version":1}},"canonical_sha256":"3012df3a3380308b1a1b364468a575285460cb28f23cdc903e15e090641a0386","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3012df3a3380308b1a1b364468a575285460cb28f23cdc903e15e090641a0386","first_computed_at":"2026-05-17T23:39:09.875853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:09.875853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+jakrHd8WAuiYSb84Tm353xwyLAPrbWyDsAH5BXyfEuAZmqcjjbfSH/xKshVzITCmo5R2Eo1oDJjkLU2khRvCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:09.876368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59aceaf57e51ed4579091503e7b782108990fb93c6dff7badd639d60f19b9c92","sha256:094a1a12fda92bb297e5761d675c2ef3188e88741cb84ac209ad4b5e4910c287"],"state_sha256":"b9a882839c49b94d05c6169f9b95078811824ff1b7c9f64e133a3a885935fabc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YU0I+07usWmItIfKqLFO2KudTxRNPwgOLM/VXWBhZPfYYPr44LgEs0FlyRFHdCqZ0EHVZYvhV1Iomsavb9dEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T01:21:42.493654Z","bundle_sha256":"dfc44d2480c05f22a49bb3cc410378c0ba6cc2de1ce7a8713a496c2f376b2428"}}