{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FC3ZZJXMIQ2LEZK2NYL3I5YHFE","short_pith_number":"pith:FC3ZZJXM","canonical_record":{"source":{"id":"2506.20260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T09:07:00Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"d8383e0da940172e2e8abc19059c214f8565910cfa4552cdd64078b10b7d4427","abstract_canon_sha256":"c105b8ec3aed6d3251211fb545a4370048bf3a99acc8d449ff17165d67331877"},"schema_version":"1.0"},"canonical_sha256":"28b79ca6ec4434b2655a6e17b477072916dd3d119825a7015a7f32dc582a773e","source":{"kind":"arxiv","id":"2506.20260","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20260","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20260v1","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20260","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"pith_short_12","alias_value":"FC3ZZJXMIQ2L","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"FC3ZZJXMIQ2LEZK2","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"FC3ZZJXM","created_at":"2026-07-05T11:27:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FC3ZZJXMIQ2LEZK2NYL3I5YHFE","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T09:07:00Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"d8383e0da940172e2e8abc19059c214f8565910cfa4552cdd64078b10b7d4427","abstract_canon_sha256":"c105b8ec3aed6d3251211fb545a4370048bf3a99acc8d449ff17165d67331877"},"schema_version":"1.0"},"canonical_sha256":"28b79ca6ec4434b2655a6e17b477072916dd3d119825a7015a7f32dc582a773e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:14.822437Z","signature_b64":"y9jybexc28AZOYE5NgNTYELBCo1HAnM6OAtyjArWtcw6Gs9A/wTr7aoN8JCjPXl5GXhGD5JhqfYHgCaTnbt/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b79ca6ec4434b2655a6e17b477072916dd3d119825a7015a7f32dc582a773e","last_reissued_at":"2026-07-05T11:27:14.822017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:14.822017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20260","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":"2026-07-05T11:27:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1bvKdMqVWwO0K295nynB5Y5CYE/MeaM32ifwIXGcxnsQblBbC+sWbiopFotl0fMiOEdJkPu8Ce+H0yS/vaHaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:44:42.988899Z"},"content_sha256":"06cffc6468e1e427fa3444481934c364a4084905d7e7302a5f6fde81cc5e0c59","schema_version":"1.0","event_id":"sha256:06cffc6468e1e427fa3444481934c364a4084905d7e7302a5f6fde81cc5e0c59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FC3ZZJXMIQ2LEZK2NYL3I5YHFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Argumentative Ensembling for Robust Recourse under Model Multiplicity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Antonio Rago, Francesca Toni, Francesco Leofante, Junqi Jiang","submitted_at":"2025-06-25T09:07:00Z","abstract_excerpt":"In machine learning, it is common to obtain multiple equally performing models for the same prediction task, e.g., when training neural networks with different random seeds. Model multiplicity (MM) is the situation which arises when these competing models differ in their predictions for the same input, for which ensembling is often employed to determine an aggregation of the outputs. Providing recourse recommendations via counterfactual explanations (CEs) under MM thus becomes complex, since the CE may not be valid across all models, i.e., the CEs are not robust under MM. In this work, we form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20260","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/2506.20260/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":"2026-07-05T11:27:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4UMUPTOQZMcRDqlzORrEtzcyFvzVg9idF+0ymPcV40ekBcj3ygKo3quDGrl9IWz4rdrMRGylrQiJewRppWAOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:44:42.989880Z"},"content_sha256":"f081d5b69c3c39debe163192614b16699db81741c26599f605de39f9a6b5f3e8","schema_version":"1.0","event_id":"sha256:f081d5b69c3c39debe163192614b16699db81741c26599f605de39f9a6b5f3e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE/bundle.json","state_url":"https://pith.science/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE/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":"2026-08-09T03:44:42Z","links":{"resolver":"https://pith.science/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE","bundle":"https://pith.science/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE/bundle.json","state":"https://pith.science/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FC3ZZJXMIQ2LEZK2NYL3I5YHFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FC3ZZJXMIQ2LEZK2NYL3I5YHFE","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":"c105b8ec3aed6d3251211fb545a4370048bf3a99acc8d449ff17165d67331877","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T09:07:00Z","title_canon_sha256":"d8383e0da940172e2e8abc19059c214f8565910cfa4552cdd64078b10b7d4427"},"schema_version":"1.0","source":{"id":"2506.20260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20260","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20260v1","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20260","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"pith_short_12","alias_value":"FC3ZZJXMIQ2L","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"FC3ZZJXMIQ2LEZK2","created_at":"2026-07-05T11:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"FC3ZZJXM","created_at":"2026-07-05T11:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:f081d5b69c3c39debe163192614b16699db81741c26599f605de39f9a6b5f3e8","target":"graph","created_at":"2026-07-05T11:27:14Z","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/2506.20260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In machine learning, it is common to obtain multiple equally performing models for the same prediction task, e.g., when training neural networks with different random seeds. Model multiplicity (MM) is the situation which arises when these competing models differ in their predictions for the same input, for which ensembling is often employed to determine an aggregation of the outputs. Providing recourse recommendations via counterfactual explanations (CEs) under MM thus becomes complex, since the CE may not be valid across all models, i.e., the CEs are not robust under MM. In this work, we form","authors_text":"Antonio Rago, Francesca Toni, Francesco Leofante, Junqi Jiang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T09:07:00Z","title":"Argumentative Ensembling for Robust Recourse under Model Multiplicity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20260","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":"sha256:06cffc6468e1e427fa3444481934c364a4084905d7e7302a5f6fde81cc5e0c59","target":"record","created_at":"2026-07-05T11:27:14Z","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":"c105b8ec3aed6d3251211fb545a4370048bf3a99acc8d449ff17165d67331877","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T09:07:00Z","title_canon_sha256":"d8383e0da940172e2e8abc19059c214f8565910cfa4552cdd64078b10b7d4427"},"schema_version":"1.0","source":{"id":"2506.20260","kind":"arxiv","version":1}},"canonical_sha256":"28b79ca6ec4434b2655a6e17b477072916dd3d119825a7015a7f32dc582a773e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28b79ca6ec4434b2655a6e17b477072916dd3d119825a7015a7f32dc582a773e","first_computed_at":"2026-07-05T11:27:14.822017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:14.822017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y9jybexc28AZOYE5NgNTYELBCo1HAnM6OAtyjArWtcw6Gs9A/wTr7aoN8JCjPXl5GXhGD5JhqfYHgCaTnbt/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:14.822437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06cffc6468e1e427fa3444481934c364a4084905d7e7302a5f6fde81cc5e0c59","sha256:f081d5b69c3c39debe163192614b16699db81741c26599f605de39f9a6b5f3e8"],"state_sha256":"00544ff7548ec9b75407517c92e35739be0d6e77e6def1668b33fdd9c51e2fbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BfjJgMhCFPns8ZvgSoV7Aa9H4fWPY6nIEPgGECJiVQWOkc+kWPgWpVPHVOFojCOc204Fh27Rt1azEx77YdAwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:44:42.995104Z","bundle_sha256":"d56e843987d3762046dd7789a1bd687a011270bc9f132a09e7fa90da0e4ec1ec"}}