{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RF4XXKDARAOPDITEXBYFRX27JW","short_pith_number":"pith:RF4XXKDA","canonical_record":{"source":{"id":"2501.14912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T20:39:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff52e04b492beb218988618b717237493def3bd0eee9e027e13ccb3ec9233913","abstract_canon_sha256":"c80a6157f48908e30b467170f9122e0bd7389ea0c68487c32487d8f47ca70592"},"schema_version":"1.0"},"canonical_sha256":"89797ba860881cf1a264b87058df5f4d9dc983fe65420519160851264e0a62fa","source":{"kind":"arxiv","id":"2501.14912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14912","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14912v1","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14912","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"RF4XXKDARAOP","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"RF4XXKDARAOPDITE","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"RF4XXKDA","created_at":"2026-07-05T10:05:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RF4XXKDARAOPDITEXBYFRX27JW","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T20:39:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff52e04b492beb218988618b717237493def3bd0eee9e027e13ccb3ec9233913","abstract_canon_sha256":"c80a6157f48908e30b467170f9122e0bd7389ea0c68487c32487d8f47ca70592"},"schema_version":"1.0"},"canonical_sha256":"89797ba860881cf1a264b87058df5f4d9dc983fe65420519160851264e0a62fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:20.672202Z","signature_b64":"lmXZltiRJ9zzQF7ZJ0AxoAMOhqwLrp/TuZhB8qUAclzHfqSew7qRF/t7qVj5VNQ9dptveGLYAeMHVpvP0r7nDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89797ba860881cf1a264b87058df5f4d9dc983fe65420519160851264e0a62fa","last_reissued_at":"2026-07-05T10:05:20.671739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:20.671739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14912","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":"2026-07-05T10:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFIEPqLoQG1qBK9bdQwaK1PNhuyvVMV5JxctCS8v4ynRQ4ZsNAyhLzMQQzPOxUoxjBlnT2TLFYSNybsFHbtZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T09:35:50.448718Z"},"content_sha256":"5325f087c7923f7abafc1588ca0a43c5b5497026e1466afb24c26bcdadf588ec","schema_version":"1.0","event_id":"sha256:5325f087c7923f7abafc1588ca0a43c5b5497026e1466afb24c26bcdadf588ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RF4XXKDARAOPDITEXBYFRX27JW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feasible Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Ignacio Hounie, Jose Gallego-Posada, Juan Elenter, Juan Ramirez, Meraj Hashemizadeh, Simon Lacoste-Julien","submitted_at":"2025-01-24T20:39:38Z","abstract_excerpt":"We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample. In contrast to the ubiquitous Empirical Risk Minimization (ERM) framework, which optimizes for average performance, FL demands satisfactory performance on every individual data point. Since any model that meets the prescribed performance threshold is a valid FL solution, the choice of optimization algorithm and its dynamics play a crucial role in shaping the properties of the resulting solutions. In particular, we study"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14912","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/2501.14912/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":"2026-07-05T10:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8Dowt0ZwU9019z+nMhXfTZtMUBVGWRSVPUfLi5JNQUanXdMlhX+AqrsaUXIpxkUyjmrNrUsxVzEjaEEUx7KAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T09:35:50.449105Z"},"content_sha256":"d1424ba2ad501bfd79b81d441ea7d0e5823f51370b06b74ab197743c299b3b73","schema_version":"1.0","event_id":"sha256:d1424ba2ad501bfd79b81d441ea7d0e5823f51370b06b74ab197743c299b3b73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RF4XXKDARAOPDITEXBYFRX27JW/bundle.json","state_url":"https://pith.science/pith/RF4XXKDARAOPDITEXBYFRX27JW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RF4XXKDARAOPDITEXBYFRX27JW/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":"2026-07-12T09:35:50Z","links":{"resolver":"https://pith.science/pith/RF4XXKDARAOPDITEXBYFRX27JW","bundle":"https://pith.science/pith/RF4XXKDARAOPDITEXBYFRX27JW/bundle.json","state":"https://pith.science/pith/RF4XXKDARAOPDITEXBYFRX27JW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RF4XXKDARAOPDITEXBYFRX27JW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RF4XXKDARAOPDITEXBYFRX27JW","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":"c80a6157f48908e30b467170f9122e0bd7389ea0c68487c32487d8f47ca70592","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T20:39:38Z","title_canon_sha256":"ff52e04b492beb218988618b717237493def3bd0eee9e027e13ccb3ec9233913"},"schema_version":"1.0","source":{"id":"2501.14912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14912","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14912v1","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14912","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"RF4XXKDARAOP","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"RF4XXKDARAOPDITE","created_at":"2026-07-05T10:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"RF4XXKDA","created_at":"2026-07-05T10:05:20Z"}],"graph_snapshots":[{"event_id":"sha256:d1424ba2ad501bfd79b81d441ea7d0e5823f51370b06b74ab197743c299b3b73","target":"graph","created_at":"2026-07-05T10:05:20Z","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/2501.14912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample. In contrast to the ubiquitous Empirical Risk Minimization (ERM) framework, which optimizes for average performance, FL demands satisfactory performance on every individual data point. Since any model that meets the prescribed performance threshold is a valid FL solution, the choice of optimization algorithm and its dynamics play a crucial role in shaping the properties of the resulting solutions. In particular, we study","authors_text":"Alejandro Ribeiro, Ignacio Hounie, Jose Gallego-Posada, Juan Elenter, Juan Ramirez, Meraj Hashemizadeh, Simon Lacoste-Julien","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T20:39:38Z","title":"Feasible Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14912","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":"sha256:5325f087c7923f7abafc1588ca0a43c5b5497026e1466afb24c26bcdadf588ec","target":"record","created_at":"2026-07-05T10:05:20Z","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":"c80a6157f48908e30b467170f9122e0bd7389ea0c68487c32487d8f47ca70592","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T20:39:38Z","title_canon_sha256":"ff52e04b492beb218988618b717237493def3bd0eee9e027e13ccb3ec9233913"},"schema_version":"1.0","source":{"id":"2501.14912","kind":"arxiv","version":1}},"canonical_sha256":"89797ba860881cf1a264b87058df5f4d9dc983fe65420519160851264e0a62fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89797ba860881cf1a264b87058df5f4d9dc983fe65420519160851264e0a62fa","first_computed_at":"2026-07-05T10:05:20.671739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:20.671739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lmXZltiRJ9zzQF7ZJ0AxoAMOhqwLrp/TuZhB8qUAclzHfqSew7qRF/t7qVj5VNQ9dptveGLYAeMHVpvP0r7nDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:20.672202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5325f087c7923f7abafc1588ca0a43c5b5497026e1466afb24c26bcdadf588ec","sha256:d1424ba2ad501bfd79b81d441ea7d0e5823f51370b06b74ab197743c299b3b73"],"state_sha256":"abf3055ee92f2e59d449199edb5dddcec9205e5e66dfc1e29a477238483bb11d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bEODlp62L2MUqll6iSV9hoy0NmV3PWiBfQshZl7v7QGabIyhksh8814zDi6MVrfo24rLAWzeGPddwOm2RZsBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T09:35:50.451851Z","bundle_sha256":"e7835d4936486fed0ebbaf3e1f3009f685ef2984811414ec55bbe460f6d7ae67"}}