{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H2M3KJ733MRYFZ3A6W24Y44MXL","short_pith_number":"pith:H2M3KJ73","canonical_record":{"source":{"id":"2604.23396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T17:58:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b2d8b74091a1eda5fbcbf95ff63dbb39e8bdbcfe97af4499246ca91f5954cbbe","abstract_canon_sha256":"ca009d26a660ddfdc83d2ad226545f6b02427f8d17ebd14270feb38aeadff4c6"},"schema_version":"1.0"},"canonical_sha256":"3e99b527fbdb2382e760f5b5cc738cbad9069278ec43b042fd2ce00c565c1087","source":{"kind":"arxiv","id":"2604.23396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.23396","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.23396v1","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23396","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"H2M3KJ733MRY","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"H2M3KJ733MRYFZ3A","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"H2M3KJ73","created_at":"2026-05-26T01:03:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H2M3KJ733MRYFZ3A6W24Y44MXL","target":"record","payload":{"canonical_record":{"source":{"id":"2604.23396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T17:58:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b2d8b74091a1eda5fbcbf95ff63dbb39e8bdbcfe97af4499246ca91f5954cbbe","abstract_canon_sha256":"ca009d26a660ddfdc83d2ad226545f6b02427f8d17ebd14270feb38aeadff4c6"},"schema_version":"1.0"},"canonical_sha256":"3e99b527fbdb2382e760f5b5cc738cbad9069278ec43b042fd2ce00c565c1087","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:31.177678Z","signature_b64":"0+Ebe5834+LR/9wGu1JJEtZGkrl3aEmbHjqHq5AYxzmEIwB8w36dUGV7izDpVTWVgNBNsiPdwL212YVN6GcXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e99b527fbdb2382e760f5b5cc738cbad9069278ec43b042fd2ce00c565c1087","last_reissued_at":"2026-05-26T01:03:31.176657Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:31.176657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.23396","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":"2026-05-26T01:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BBdzC9eJuegrjorqMUwpmZUmvL8TvjXJ6s8t0v8FdfnA5ZMpuzsfJ/M5k4zo/qyFHq/0j1RCdmq9un3ayg8fBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:00:34.914091Z"},"content_sha256":"df769da1f696a01e5dafc9ae9f93cb46f6d69b3ff28822e1139d1da89010411f","schema_version":"1.0","event_id":"sha256:df769da1f696a01e5dafc9ae9f93cb46f6d69b3ff28822e1139d1da89010411f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H2M3KJ733MRYFZ3A6W24Y44MXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PAG's planning signal in generative retrieval collapses under intent-preserving typos.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Kidist Amde Mekonnen, Maarten de Rijke, Simon Lupart, Yongkang Li, Yubao Tang","submitted_at":"2026-04-25T17:58:15Z","abstract_excerpt":"Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam decoding. Planning Ahead in Generative Retrieval (PAG) mitigates this failure mode by using simultaneous decoding to compute a document-level look-ahead prior that guides subsequent sequential decoding. We reproduce PAG at inference time and stress-test its decoding behavior. Using the authors' released checkpoint and identifier/trie artifacts under the reported de"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PAG's planning signal is brittle under lexical surface-form variation: intent-preserving typos can trigger plan collapse, where the planned candidate pool shifts enough that the look-ahead bonus provides little useful guidance, effectively reverting decoding toward weaker unguided search.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the plan drift diagnostics and cross-lingual tests isolate the stability of the planning signal without being confounded by specific beam sizes, trie construction details, or unstated differences between the released checkpoint and the original training run.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PAG's planning signal in generative retrieval collapses under intent-preserving typos.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"68d8a8256c5bcad1760330f41c093eb9b512a3c31faf3e1521a498d6247f986f"},"source":{"id":"2604.23396","kind":"arxiv","version":1},"verdict":{"id":"81aed4a1-5cc2-4913-bc11-904ea6c35a98","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T07:24:32.653355Z","strongest_claim":"PAG's planning signal is brittle under lexical surface-form variation: intent-preserving typos can trigger plan collapse, where the planned candidate pool shifts enough that the look-ahead bonus provides little useful guidance, effectively reverting decoding toward weaker unguided search.","one_line_summary":"Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the plan drift diagnostics and cross-lingual tests isolate the stability of the planning signal without being confounded by specific beam sizes, trie construction details, or unstated differences between the released checkpoint and the original training run.","pith_extraction_headline":"PAG's planning signal in generative retrieval collapses under intent-preserving typos."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.23396/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T08:41:25.107579Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:14:07.459525Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7fae96686f880b3cc82f7b07378702622d1d6f188d0c18fc72cb27c286caed85"},"references":{"count":44,"sample":[{"doi":"","year":2022,"title":"Michele Bevilacqua, Marco Maru, and Fabio Petroni. 2022. Autoregressive Search Engines: Generating Substrings as Document Identifiers. InAdvances in Neural Information Processing Systems (NeurIPS)","work_id":"","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"arXiv preprint arXiv:2108.13897 , year=","work_id":"e8dc400e-4c9b-4e56-9cb0-5a26cdc4d7bb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Steven Dong, Yubao Tang, and Maarten de Rijke. 2026. Multi-Step Semantic Rea- soning in Generative Retrieval. InEuropean Conference on Information Retrieval. Springer, 273–281","work_id":"","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Sid- dharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaud- hary, Naman Goyal, Tom Birch, Vitaliy Liptchinsk","work_id":"","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2024.findings-emnlp.248","year":2024,"title":"Tim Hagen, Harrisen Scells, and Martin Potthast. 2024. Revisiting Query Variation Robustness of Transformer Models. InFindings of the Association for Computa- tional Linguistics: EMNLP 2024, Yaser Al-","work_id":"4632124a-6ff1-450d-a443-02782b2b59b0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":30,"snapshot_sha256":"637c7b78e013eeda0757fa3406690301728032bddbe065a9525d15fe6ffeb8e0","internal_anchors":2},"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":"81aed4a1-5cc2-4913-bc11-904ea6c35a98"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwLwZl9F8rJO47BUDp1/2YhlXRKbF3F7sVXyqVfYbALN/lG4Hqi+iMi9niTYmDJ50hhnRGgiTADZ1M+5TysRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:00:34.915404Z"},"content_sha256":"53eb494d9078a427ac9f6ee55a18b0b08b23e1d91ba8c226003079d798b8a828","schema_version":"1.0","event_id":"sha256:53eb494d9078a427ac9f6ee55a18b0b08b23e1d91ba8c226003079d798b8a828"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2M3KJ733MRYFZ3A6W24Y44MXL/bundle.json","state_url":"https://pith.science/pith/H2M3KJ733MRYFZ3A6W24Y44MXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2M3KJ733MRYFZ3A6W24Y44MXL/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":"2026-06-06T20:00:34Z","links":{"resolver":"https://pith.science/pith/H2M3KJ733MRYFZ3A6W24Y44MXL","bundle":"https://pith.science/pith/H2M3KJ733MRYFZ3A6W24Y44MXL/bundle.json","state":"https://pith.science/pith/H2M3KJ733MRYFZ3A6W24Y44MXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2M3KJ733MRYFZ3A6W24Y44MXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H2M3KJ733MRYFZ3A6W24Y44MXL","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":"ca009d26a660ddfdc83d2ad226545f6b02427f8d17ebd14270feb38aeadff4c6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T17:58:15Z","title_canon_sha256":"b2d8b74091a1eda5fbcbf95ff63dbb39e8bdbcfe97af4499246ca91f5954cbbe"},"schema_version":"1.0","source":{"id":"2604.23396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.23396","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.23396v1","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23396","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"H2M3KJ733MRY","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"H2M3KJ733MRYFZ3A","created_at":"2026-05-26T01:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"H2M3KJ73","created_at":"2026-05-26T01:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:53eb494d9078a427ac9f6ee55a18b0b08b23e1d91ba8c226003079d798b8a828","target":"graph","created_at":"2026-05-26T01:03:31Z","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":"PAG's planning signal is brittle under lexical surface-form variation: intent-preserving typos can trigger plan collapse, where the planned candidate pool shifts enough that the look-ahead bonus provides little useful guidance, effectively reverting decoding toward weaker unguided search."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the plan drift diagnostics and cross-lingual tests isolate the stability of the planning signal without being confounded by specific beam sizes, trie construction details, or unstated differences between the released checkpoint and the original training run."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PAG's planning signal in generative retrieval collapses under intent-preserving typos."}],"snapshot_sha256":"68d8a8256c5bcad1760330f41c093eb9b512a3c31faf3e1521a498d6247f986f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T08:41:25.107579Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:14:07.459525Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.23396/integrity.json","findings":[],"snapshot_sha256":"7fae96686f880b3cc82f7b07378702622d1d6f188d0c18fc72cb27c286caed85","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam decoding. Planning Ahead in Generative Retrieval (PAG) mitigates this failure mode by using simultaneous decoding to compute a document-level look-ahead prior that guides subsequent sequential decoding. We reproduce PAG at inference time and stress-test its decoding behavior. Using the authors' released checkpoint and identifier/trie artifacts under the reported de","authors_text":"Kidist Amde Mekonnen, Maarten de Rijke, Simon Lupart, Yongkang Li, Yubao Tang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"PAG's planning signal in generative retrieval collapses under intent-preserving typos.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T17:58:15Z","title":"Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval"},"references":{"count":44,"internal_anchors":2,"resolved_work":30,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Michele Bevilacqua, Marco Maru, and Fabio Petroni. 2022. Autoregressive Search Engines: Generating Substrings as Document Identifiers. InAdvances in Neural Information Processing Systems (NeurIPS)","work_id":"","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2108.13897 , year=","work_id":"e8dc400e-4c9b-4e56-9cb0-5a26cdc4d7bb","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Steven Dong, Yubao Tang, and Maarten de Rijke. 2026. Multi-Step Semantic Rea- soning in Generative Retrieval. InEuropean Conference on Information Retrieval. Springer, 273–281","work_id":"","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Sid- dharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaud- hary, Naman Goyal, Tom Birch, Vitaliy Liptchinsk","work_id":"","year":2021},{"cited_arxiv_id":"","doi":"10.18653/v1/2024.findings-emnlp.248","is_internal_anchor":false,"ref_index":5,"title":"Tim Hagen, Harrisen Scells, and Martin Potthast. 2024. Revisiting Query Variation Robustness of Transformer Models. InFindings of the Association for Computa- tional Linguistics: EMNLP 2024, Yaser Al-","work_id":"4632124a-6ff1-450d-a443-02782b2b59b0","year":2024}],"snapshot_sha256":"637c7b78e013eeda0757fa3406690301728032bddbe065a9525d15fe6ffeb8e0"},"source":{"id":"2604.23396","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-08T07:24:32.653355Z","id":"81aed4a1-5cc2-4913-bc11-904ea6c35a98","model_set":{"reader":"grok-4.3"},"one_line_summary":"Reproduction confirms PAG boosts generative retrieval effectiveness, but its look-ahead planning signal collapses under intent-preserving typos and query mismatches, reverting performance to unguided decoding.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PAG's planning signal in generative retrieval collapses under intent-preserving typos.","strongest_claim":"PAG's planning signal is brittle under lexical surface-form variation: intent-preserving typos can trigger plan collapse, where the planned candidate pool shifts enough that the look-ahead bonus provides little useful guidance, effectively reverting decoding toward weaker unguided search.","weakest_assumption":"That the plan drift diagnostics and cross-lingual tests isolate the stability of the planning signal without being confounded by specific beam sizes, trie construction details, or unstated differences between the released checkpoint and the original training run."}},"verdict_id":"81aed4a1-5cc2-4913-bc11-904ea6c35a98"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:df769da1f696a01e5dafc9ae9f93cb46f6d69b3ff28822e1139d1da89010411f","target":"record","created_at":"2026-05-26T01:03:31Z","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":"ca009d26a660ddfdc83d2ad226545f6b02427f8d17ebd14270feb38aeadff4c6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T17:58:15Z","title_canon_sha256":"b2d8b74091a1eda5fbcbf95ff63dbb39e8bdbcfe97af4499246ca91f5954cbbe"},"schema_version":"1.0","source":{"id":"2604.23396","kind":"arxiv","version":1}},"canonical_sha256":"3e99b527fbdb2382e760f5b5cc738cbad9069278ec43b042fd2ce00c565c1087","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e99b527fbdb2382e760f5b5cc738cbad9069278ec43b042fd2ce00c565c1087","first_computed_at":"2026-05-26T01:03:31.176657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:31.176657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0+Ebe5834+LR/9wGu1JJEtZGkrl3aEmbHjqHq5AYxzmEIwB8w36dUGV7izDpVTWVgNBNsiPdwL212YVN6GcXDA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:31.177678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.23396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df769da1f696a01e5dafc9ae9f93cb46f6d69b3ff28822e1139d1da89010411f","sha256:53eb494d9078a427ac9f6ee55a18b0b08b23e1d91ba8c226003079d798b8a828"],"state_sha256":"788ad51f587901f032511f683c7baead56e45fdedfea43c0c4a8abb0c1483634"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sT5yoEvz0V6AVHOjBaLPbzivupj3v4x+H25oCO1+S8ScIZ1yBM5ZttHccChRcH0btHL/PYXL6GKexGxm2lB6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:00:34.920824Z","bundle_sha256":"98cb907541721de6e99df2056242967f492adc63eabab47c4204470429922c0d"}}