{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XIRRZ4NEE3HHSLN2PE2NYWFFXC","short_pith_number":"pith:XIRRZ4NE","canonical_record":{"source":{"id":"2605.12693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T19:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"fd8a84f7e0bd15919b058ff22f259f13ba9138e0daf6676e61b66a11a1568e4e","abstract_canon_sha256":"fe1830c9c21a32e1f45ed1ca7861ede2745fd967160ea4d2a4293a8bc4e8c61a"},"schema_version":"1.0"},"canonical_sha256":"ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a","source":{"kind":"arxiv","id":"2605.12693","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12693","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12693v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12693","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"XIRRZ4NEE3HH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XIRRZ4NEE3HHSLN2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XIRRZ4NE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XIRRZ4NEE3HHSLN2PE2NYWFFXC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T19:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"fd8a84f7e0bd15919b058ff22f259f13ba9138e0daf6676e61b66a11a1568e4e","abstract_canon_sha256":"fe1830c9c21a32e1f45ed1ca7861ede2745fd967160ea4d2a4293a8bc4e8c61a"},"schema_version":"1.0"},"canonical_sha256":"ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:49.808055Z","signature_b64":"1XfT5B1hXrTclXj9OKvl4ocyAO7GTKuEMV4gHR2SGvz/kS7ubF38MmVyqJPxS+HFdE0pO+HFYe6F4yWSd0lkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a","last_reissued_at":"2026-05-18T03:09:49.807248Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:49.807248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12693","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":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0wbtxiA/IbS2pwGNYKmXGd57TmEgMyq4bM8YcP1hjaaQfv0xoXjSdfVah8yaTxy+Lh2kvu3OYwLR4AgXcSwCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T00:24:56.738135Z"},"content_sha256":"6d1e5ba822c621bd8719bdb15920354b420d0c956e486f26ec7db0e2f56e675f","schema_version":"1.0","event_id":"sha256:6d1e5ba822c621bd8719bdb15920354b420d0c956e486f26ec7db0e2f56e675f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XIRRZ4NEE3HHSLN2PE2NYWFFXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero","submitted_at":"2026-05-12T19:43:49Z","abstract_excerpt":"Decision-focused learning trains predictive models end-to-end against downstream decision loss, but online settings suffer delayed feedback: outcomes may not arrive for many environment interactions. We identify \\emph{staleness amplification}, a failure mode unique to bilevel optimization under delay, in which gradient staleness couples with inner-solver sensitivity to inflate regret beyond single-level delay theory. We prove that any black-box delayed optimizer incurs an irreducible regret cost from inner-solver approximation error, and that gradient staleness contributes a quadratically grow"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"IGT-OMD achieves the first sublinear regret bound for delayed bilevel optimization with queue-length-adaptive step sizes by reducing transport error from quadratic to linear dependence on delay.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That inner solutions can be stored and re-evaluated at current parameters with negligible extra cost and that the bilevel problem satisfies the smoothness and convexity conditions needed for the regret analysis to go through.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3d27e44032881670387e6a6ac7fa6fc7976efda9282217cd3c46d6274baa01cb"},"source":{"id":"2605.12693","kind":"arxiv","version":1},"verdict":{"id":"8f86830b-418b-41bc-a2c4-eae6fe4b7653","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:00:32.254926Z","strongest_claim":"IGT-OMD achieves the first sublinear regret bound for delayed bilevel optimization with queue-length-adaptive step sizes by reducing transport error from quadratic to linear dependence on delay.","one_line_summary":"IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That inner solutions can be stored and re-evaluated at current parameters with negligible extra cost and that the bilevel problem satisfies the smoothness and convexity conditions needed for the regret analysis to go through.","pith_extraction_headline":"IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions."},"references":{"count":43,"sample":[{"doi":"10.1287/mnsc.2020.3922","year":2022,"title":"Adam N. Elmachtoub and Paul Grigas. Smart “Predict, then Optimize”.Management Science, 68(1):9–26, 2022. doi: 10.1287/mnsc.2020.3922","work_id":"1d367d07-9caa-459c-a28c-8c2f98a58c01","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1609/aaai.v33i01","year":2019,"title":"Melding the data-decisions pipeline: Decision- focused learning for combinatorial optimization","work_id":"15e6042d-4da3-4672-a28c-8bb3a3ce644a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Decision-focused learning: Foundations, state of the art, benchmark and future opportunities.Journal of Artificial Intelligence Research, 81:1623–1701, 2024","work_id":"e88758ea-7402-4199-a2cd-3acb11457338","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Online learning under delayed feedback","work_id":"61dd1aaa-43c4-4c48-a334-5b085d37244c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Online learning and online convex optimization.Foundations and Trends in Machine Learning, 4(2):107–194","work_id":"3bd3c6eb-fd04-4237-95c3-1ada8bc8a1ae","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":43,"snapshot_sha256":"3f0569b265d25d679f0baa4762bf968c9108f42a61e9ca78cee3cc70962dcf03","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0dd4b6dd7147c262c070828b81601954cdbbdead2e53649b1ade512add586e18"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"8f86830b-418b-41bc-a2c4-eae6fe4b7653"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aCQUgb54E3IqHt0HMvmDSZh9hevvbdGj4HclgjnbGN4+tVscQ/jc7AtqEVSUMN4oXEbePTbh5ZyGksEcidgQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T00:24:56.739412Z"},"content_sha256":"0a8425d9cc9ec1534ccde601d34d5f37ce29b055ff7d8a07f2a66c04782e840f","schema_version":"1.0","event_id":"sha256:0a8425d9cc9ec1534ccde601d34d5f37ce29b055ff7d8a07f2a66c04782e840f"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:XIRRZ4NEE3HHSLN2PE2NYWFFXC","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arXiv.2602.02634.URLhttps://arxiv.org/abs/2602.02634.10) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Alexander Ryabchenko, Idan Attias, and Daniel M. Roy. A reduction from delayed to immediate feedback for online convex optimization with improved guarantees. InProceedings of the AAAI Conference on Artificial Intelligence, volume 40 (01), p","arxiv_id":"2605.12693","detector":"doi_compliance","evidence":{"ref_index":16,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Alexander Ryabchenko, Idan Attias, and Daniel M. Roy. A reduction from delayed to immediate feedback for online convex optimization with improved guarantees. InProceedings of the AAAI Conference on Artificial Intelligence, volume 40 (01), p","reconstructed_doi":"10.48550/arXiv.2602.02634.URLhttps://arxiv.org/abs/2602.02634.10"},"severity":"advisory","ref_index":16,"audited_at":"2026-05-19T07:12:44.747304Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arXiv.2602.02634.URLhttps://arxiv.org/abs/2602.02634.10","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"74b1addd6fa77ea721739426aede09a015a48d77a77365cf9d1aa2a866bee191","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":278,"payload_sha256":"1cc9a275757e9bd7f217e178388233f43ddd277a8bc7378b473fecf3a6be65ba","signature_b64":"aZxwuiNpQ0AC77/KH1odj38wEjVo9rX8kL94Io8eqre1MU6ADbrHQTxMOEoUWuNME9SQ8GAE86rLFdW3WAR2Dw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T07:16:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWuasr9WcU8jTw3Vk/Wrg09vXl6Z1Zf6VN7oeiWPx7p03WRWnYgf1W2LC08MjKslhUPylrTvv9VOURHJHfceBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T00:24:56.741245Z"},"content_sha256":"75834a189eabbbb033836508da76dc24596ac4906983b76e5325e228451a1945","schema_version":"1.0","event_id":"sha256:75834a189eabbbb033836508da76dc24596ac4906983b76e5325e228451a1945"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC/bundle.json","state_url":"https://pith.science/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC/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":"2026-05-20T00:24:56Z","links":{"resolver":"https://pith.science/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC","bundle":"https://pith.science/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC/bundle.json","state":"https://pith.science/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XIRRZ4NEE3HHSLN2PE2NYWFFXC","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe1830c9c21a32e1f45ed1ca7861ede2745fd967160ea4d2a4293a8bc4e8c61a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T19:43:49Z","title_canon_sha256":"fd8a84f7e0bd15919b058ff22f259f13ba9138e0daf6676e61b66a11a1568e4e"},"schema_version":"1.0","source":{"id":"2605.12693","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12693","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12693v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12693","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"XIRRZ4NEE3HH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XIRRZ4NEE3HHSLN2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XIRRZ4NE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0a8425d9cc9ec1534ccde601d34d5f37ce29b055ff7d8a07f2a66c04782e840f","target":"graph","created_at":"2026-05-18T03:09:49Z","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":"IGT-OMD achieves the first sublinear regret bound for delayed bilevel optimization with queue-length-adaptive step sizes by reducing transport error from quadratic to linear dependence on delay."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That inner solutions can be stored and re-evaluated at current parameters with negligible extra cost and that the bilevel problem satisfies the smoothness and convexity conditions needed for the regret analysis to go through."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions."}],"snapshot_sha256":"3d27e44032881670387e6a6ac7fa6fc7976efda9282217cd3c46d6274baa01cb"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0dd4b6dd7147c262c070828b81601954cdbbdead2e53649b1ade512add586e18"},"paper":{"abstract_excerpt":"Decision-focused learning trains predictive models end-to-end against downstream decision loss, but online settings suffer delayed feedback: outcomes may not arrive for many environment interactions. We identify \\emph{staleness amplification}, a failure mode unique to bilevel optimization under delay, in which gradient staleness couples with inner-solver sensitivity to inflate regret beyond single-level delay theory. We prove that any black-box delayed optimizer incurs an irreducible regret cost from inner-solver approximation error, and that gradient staleness contributes a quadratically grow","authors_text":"Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero","cross_cats":[],"headline":"IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T19:43:49Z","title":"IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback"},"references":{"count":43,"internal_anchors":4,"resolved_work":43,"sample":[{"cited_arxiv_id":"","doi":"10.1287/mnsc.2020.3922","is_internal_anchor":false,"ref_index":1,"title":"Adam N. Elmachtoub and Paul Grigas. Smart “Predict, then Optimize”.Management Science, 68(1):9–26, 2022. doi: 10.1287/mnsc.2020.3922","work_id":"1d367d07-9caa-459c-a28c-8c2f98a58c01","year":2022},{"cited_arxiv_id":"","doi":"10.1609/aaai.v33i01","is_internal_anchor":false,"ref_index":2,"title":"Melding the data-decisions pipeline: Decision- focused learning for combinatorial optimization","work_id":"15e6042d-4da3-4672-a28c-8bb3a3ce644a","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Decision-focused learning: Foundations, state of the art, benchmark and future opportunities.Journal of Artificial Intelligence Research, 81:1623–1701, 2024","work_id":"e88758ea-7402-4199-a2cd-3acb11457338","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Online learning under delayed feedback","work_id":"61dd1aaa-43c4-4c48-a334-5b085d37244c","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Online learning and online convex optimization.Foundations and Trends in Machine Learning, 4(2):107–194","work_id":"3bd3c6eb-fd04-4237-95c3-1ada8bc8a1ae","year":2012}],"snapshot_sha256":"3f0569b265d25d679f0baa4762bf968c9108f42a61e9ca78cee3cc70962dcf03"},"source":{"id":"2605.12693","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T21:00:32.254926Z","id":"8f86830b-418b-41bc-a2c4-eae6fe4b7653","model_set":{"reader":"grok-4.3"},"one_line_summary":"IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions.","strongest_claim":"IGT-OMD achieves the first sublinear regret bound for delayed bilevel optimization with queue-length-adaptive step sizes by reducing transport error from quadratic to linear dependence on delay.","weakest_assumption":"That inner solutions can be stored and re-evaluated at current parameters with negligible extra cost and that the bilevel problem satisfies the smoothness and convexity conditions needed for the regret analysis to go through."}},"verdict_id":"8f86830b-418b-41bc-a2c4-eae6fe4b7653"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6d1e5ba822c621bd8719bdb15920354b420d0c956e486f26ec7db0e2f56e675f","target":"record","created_at":"2026-05-18T03:09:49Z","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":"fe1830c9c21a32e1f45ed1ca7861ede2745fd967160ea4d2a4293a8bc4e8c61a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T19:43:49Z","title_canon_sha256":"fd8a84f7e0bd15919b058ff22f259f13ba9138e0daf6676e61b66a11a1568e4e"},"schema_version":"1.0","source":{"id":"2605.12693","kind":"arxiv","version":1}},"canonical_sha256":"ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a","first_computed_at":"2026-05-18T03:09:49.807248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:49.807248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1XfT5B1hXrTclXj9OKvl4ocyAO7GTKuEMV4gHR2SGvz/kS7ubF38MmVyqJPxS+HFdE0pO+HFYe6F4yWSd0lkCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:49.808055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12693","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d1e5ba822c621bd8719bdb15920354b420d0c956e486f26ec7db0e2f56e675f","sha256:0a8425d9cc9ec1534ccde601d34d5f37ce29b055ff7d8a07f2a66c04782e840f","sha256:75834a189eabbbb033836508da76dc24596ac4906983b76e5325e228451a1945"],"state_sha256":"03771f9ab4250c7c536426b0fb61905e04704b1059d7b8901d4738ba2452348c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAi1uYi7Cs+/xJkdxrE0WaNgcf11/Vfz0ja1TBLSsXawTIWW1oSCrTNfl1dNcRVHP1HgUh65OMLlnUBdaiwDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T00:24:56.746882Z","bundle_sha256":"5030f2fbc52b4d3d026a0879e50ee24c335200c85b1fb801e070ee9407db391c"}}