{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SPXEBG6S3HEMQMNL4342VK2377","short_pith_number":"pith:SPXEBG6S","canonical_record":{"source":{"id":"2605.04970","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-06T14:27:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eaf65003074448d82097cf0cb8bfcad3c9dfe2c0443a06e3a9096a73c1e91a5e","abstract_canon_sha256":"20a2ba7a276103402d440f2cc86dd85696c2dca5ff913c3cc6490f490b843dea"},"schema_version":"1.0"},"canonical_sha256":"93ee409bd2d9c8c831abe6f9aaab5bffc0b50083bfae51650f149a540bcdc680","source":{"kind":"arxiv","id":"2605.04970","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04970","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04970v2","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04970","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"SPXEBG6S3HEM","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"SPXEBG6S3HEMQMNL","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"SPXEBG6S","created_at":"2026-05-20T02:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SPXEBG6S3HEMQMNL4342VK2377","target":"record","payload":{"canonical_record":{"source":{"id":"2605.04970","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-06T14:27:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eaf65003074448d82097cf0cb8bfcad3c9dfe2c0443a06e3a9096a73c1e91a5e","abstract_canon_sha256":"20a2ba7a276103402d440f2cc86dd85696c2dca5ff913c3cc6490f490b843dea"},"schema_version":"1.0"},"canonical_sha256":"93ee409bd2d9c8c831abe6f9aaab5bffc0b50083bfae51650f149a540bcdc680","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:44.318485Z","signature_b64":"Jv3ecWahSVDkhTi4+RinDcTwFPIRul5ozEgguNsIGGsR7TxSK9wyVpeQs28xDvO4SgwVWGVilYnGG2QypwuXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93ee409bd2d9c8c831abe6f9aaab5bffc0b50083bfae51650f149a540bcdc680","last_reissued_at":"2026-05-20T02:05:44.317585Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:44.317585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.04970","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JEadLmR1YHHloFjn9bNf3ShET1lNsdezvI6NOKunNVrJcrz7UL+oTnQ59xzSA+DFwQTYwxW+RpFWwONMoasQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:21:47.225621Z"},"content_sha256":"15ea91b3665a71860f6ac64fb03d70bc4d41c0ff77a7db8fa098c1583b0d2820","schema_version":"1.0","event_id":"sha256:15ea91b3665a71860f6ac64fb03d70bc4d41c0ff77a7db8fa098c1583b0d2820"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SPXEBG6S3HEMQMNL4342VK2377","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skill Neologisms: Towards Skill-based Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Skill neologisms let LLMs gain new abilities by adding optimized soft tokens to the vocabulary without any weight updates.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonin Berthon, Mihaela van der Schaar, Nicolas Astorga","submitted_at":"2026-05-06T14:27:12Z","abstract_excerpt":"Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and parameter-efficient variants risk catastrophic forgetting, while context-based approaches have limited expressiveness and are constrained by the model's effective context. We explore skill neologisms--soft tokens integrated in the model's vocabulary and optimized to improve capabilities over a specific skill--as a way to selectively acquire new skills without weight updates. W"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We then show that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That independently optimized skill neologisms can be added and composed without degrading the base model's performance on unrelated tasks or causing interference between skills.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Skill neologisms are optimized soft tokens that improve LLM performance on targeted skills without weight updates and allow zero-shot composition for continual learning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Skill neologisms let LLMs gain new abilities by adding optimized soft tokens to the vocabulary without any weight updates.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"565c99aece2e655cf262b764f6dced6bf11e3cac5d72d32e4d6f42152ea236e9"},"source":{"id":"2605.04970","kind":"arxiv","version":2},"verdict":{"id":"9ce6e16c-e00a-4765-b368-62598d83ebb0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T17:22:13.566506Z","strongest_claim":"We then show that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.","one_line_summary":"Skill neologisms are optimized soft tokens that improve LLM performance on targeted skills without weight updates and allow zero-shot composition for continual learning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That independently optimized skill neologisms can be added and composed without degrading the base model's performance on unrelated tasks or causing interference between skills.","pith_extraction_headline":"Skill neologisms let LLMs gain new abilities by adding optimized soft tokens to the vocabulary without any weight updates."},"integrity":{"clean":false,"summary":{"advisory":1,"critical":0,"by_detector":{"doi_compliance":{"total":1,"advisory":1,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2605.04970/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.aiopen.2023.08.012.Liu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":9,"audited_at":"2026-05-19T13:59:30.419833Z","detected_doi":"10.1016/j.aiopen.2023.08.012.Liu","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.906526Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:59:30.419833Z","status":"completed","version":"1.0.0","findings_count":1}],"snapshot_sha256":"7400532a3959b0907a6422654af3b1c2d47062eb5610e3a4934846f7a7f46411"},"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":"9ce6e16c-e00a-4765-b368-62598d83ebb0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ya7pcXgcb1Z1K0FgJMMyphM0K0PwLUn6YJtDXCI4h1SIR35xuDUWOY/Tq49dtgC9NDKEQ365I3HlcqoPKoMfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:21:47.226155Z"},"content_sha256":"77dcb52dd120da87e63303d1d637f81cf614c55a6d2f7b1b63d262d5eae48da1","schema_version":"1.0","event_id":"sha256:77dcb52dd120da87e63303d1d637f81cf614c55a6d2f7b1b63d262d5eae48da1"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:SPXEBG6S3HEMQMNL4342VK2377","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.aiopen.2023.08.012.Liu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"ISSN 2666-6510. doi: https://doi.org/10.1016/j. aiopen.2023.08.012. Liu, Z., Liu, Q., Guo, T., Chen, J., Huang, S., Zhao, X., Tang, J., Luo, W., and Weng, J. Xes3g5m: A knowledge tracing benchmark dataset with auxiliary information. NeurIPS","arxiv_id":"2605.04970","detector":"doi_compliance","evidence":{"ref_index":9,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"ISSN 2666-6510. doi: https://doi.org/10.1016/j. aiopen.2023.08.012. Liu, Z., Liu, Q., Guo, T., Chen, J., Huang, S., Zhao, X., Tang, J., Luo, W., and Weng, J. Xes3g5m: A knowledge tracing benchmark dataset with auxiliary information. NeurIPS","reconstructed_doi":"10.1016/j.aiopen.2023.08.012.Liu"},"severity":"advisory","ref_index":9,"audited_at":"2026-05-19T13:59:30.419833Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.aiopen.2023.08.012.Liu","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"af52fec71b077ce77676a0469d6217e9762a3f8f5e497658d02d07ec30490c40","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1580,"payload_sha256":"147edbabc6ec688c31fe3ffbab0839acabe72d31eab60fa49cd7dc3317b9182b","signature_b64":"Gdr646C74zSD6pxj9agBzRTdvQzn0oeqZ5INxSZsM4YbjJtnRVYMrC5N6nIJ18aT3TI5SplPly6OSkBMyMfhDg==","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":"2026-05-19T14:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZg9ZyR4wgD/n7Vsyu49oZOBDVy3dYwMBywz3+SMa2NCBmPTv9AzivtWeNCc+21TE8BjP/25uEEyt/eRsKDOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:21:47.227045Z"},"content_sha256":"32a07da32e3b2ce4e0cb2d0866038a2cafa1dd2c534fec277c99e097434894b6","schema_version":"1.0","event_id":"sha256:32a07da32e3b2ce4e0cb2d0866038a2cafa1dd2c534fec277c99e097434894b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPXEBG6S3HEMQMNL4342VK2377/bundle.json","state_url":"https://pith.science/pith/SPXEBG6S3HEMQMNL4342VK2377/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPXEBG6S3HEMQMNL4342VK2377/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":"2026-05-21T06:21:47Z","links":{"resolver":"https://pith.science/pith/SPXEBG6S3HEMQMNL4342VK2377","bundle":"https://pith.science/pith/SPXEBG6S3HEMQMNL4342VK2377/bundle.json","state":"https://pith.science/pith/SPXEBG6S3HEMQMNL4342VK2377/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPXEBG6S3HEMQMNL4342VK2377/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SPXEBG6S3HEMQMNL4342VK2377","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":"20a2ba7a276103402d440f2cc86dd85696c2dca5ff913c3cc6490f490b843dea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-06T14:27:12Z","title_canon_sha256":"eaf65003074448d82097cf0cb8bfcad3c9dfe2c0443a06e3a9096a73c1e91a5e"},"schema_version":"1.0","source":{"id":"2605.04970","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04970","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04970v2","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04970","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"SPXEBG6S3HEM","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"SPXEBG6S3HEMQMNL","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"SPXEBG6S","created_at":"2026-05-20T02:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:77dcb52dd120da87e63303d1d637f81cf614c55a6d2f7b1b63d262d5eae48da1","target":"graph","created_at":"2026-05-20T02:05:44Z","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":"We then show that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That independently optimized skill neologisms can be added and composed without degrading the base model's performance on unrelated tasks or causing interference between skills."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Skill neologisms are optimized soft tokens that improve LLM performance on targeted skills without weight updates and allow zero-shot composition for continual learning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Skill neologisms let LLMs gain new abilities by adding optimized soft tokens to the vocabulary without any weight updates."}],"snapshot_sha256":"565c99aece2e655cf262b764f6dced6bf11e3cac5d72d32e4d6f42152ea236e9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.906526Z","status":"completed","version":"1.0.0"},{"findings_count":1,"name":"doi_compliance","ran_at":"2026-05-19T13:59:30.419833Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.04970/integrity.json","findings":[{"audited_at":"2026-05-19T13:59:30.419833Z","detected_arxiv_id":null,"detected_doi":"10.1016/j.aiopen.2023.08.012.Liu","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.aiopen.2023.08.012.Liu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":9,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"7400532a3959b0907a6422654af3b1c2d47062eb5610e3a4934846f7a7f46411","summary":{"advisory":1,"by_detector":{"doi_compliance":{"advisory":1,"critical":0,"informational":0,"total":1}},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and parameter-efficient variants risk catastrophic forgetting, while context-based approaches have limited expressiveness and are constrained by the model's effective context. We explore skill neologisms--soft tokens integrated in the model's vocabulary and optimized to improve capabilities over a specific skill--as a way to selectively acquire new skills without weight updates. W","authors_text":"Antonin Berthon, Mihaela van der Schaar, Nicolas Astorga","cross_cats":["cs.AI"],"headline":"Skill neologisms let LLMs gain new abilities by adding optimized soft tokens to the vocabulary without any weight updates.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-06T14:27:12Z","title":"Skill Neologisms: Towards Skill-based Continual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.04970","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T17:22:13.566506Z","id":"9ce6e16c-e00a-4765-b368-62598d83ebb0","model_set":{"reader":"grok-4.3"},"one_line_summary":"Skill neologisms are optimized soft tokens that improve LLM performance on targeted skills without weight updates and allow zero-shot composition for continual learning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Skill neologisms let LLMs gain new abilities by adding optimized soft tokens to the vocabulary without any weight updates.","strongest_claim":"We then show that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.","weakest_assumption":"That independently optimized skill neologisms can be added and composed without degrading the base model's performance on unrelated tasks or causing interference between skills."}},"verdict_id":"9ce6e16c-e00a-4765-b368-62598d83ebb0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:15ea91b3665a71860f6ac64fb03d70bc4d41c0ff77a7db8fa098c1583b0d2820","target":"record","created_at":"2026-05-20T02:05:44Z","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":"20a2ba7a276103402d440f2cc86dd85696c2dca5ff913c3cc6490f490b843dea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-06T14:27:12Z","title_canon_sha256":"eaf65003074448d82097cf0cb8bfcad3c9dfe2c0443a06e3a9096a73c1e91a5e"},"schema_version":"1.0","source":{"id":"2605.04970","kind":"arxiv","version":2}},"canonical_sha256":"93ee409bd2d9c8c831abe6f9aaab5bffc0b50083bfae51650f149a540bcdc680","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93ee409bd2d9c8c831abe6f9aaab5bffc0b50083bfae51650f149a540bcdc680","first_computed_at":"2026-05-20T02:05:44.317585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:44.317585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jv3ecWahSVDkhTi4+RinDcTwFPIRul5ozEgguNsIGGsR7TxSK9wyVpeQs28xDvO4SgwVWGVilYnGG2QypwuXCw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:44.318485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04970","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32a07da32e3b2ce4e0cb2d0866038a2cafa1dd2c534fec277c99e097434894b6","sha256:15ea91b3665a71860f6ac64fb03d70bc4d41c0ff77a7db8fa098c1583b0d2820","sha256:77dcb52dd120da87e63303d1d637f81cf614c55a6d2f7b1b63d262d5eae48da1"],"state_sha256":"1373609eb5ebb0433772cf28a29df9dcab311c5ce324192275d001999129e965"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MNDqco7LrezYDOn34wvdFcAMYjQwVGfLPWuCU5tanunIVK66tOvVPsZm8REWgNmkJH/FsDYlgfRrl2VGxp6jDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T06:21:47.229384Z","bundle_sha256":"e4fad6e8983127e41bcd6263b58d2391109b72747716c999d3de1230b562c9a8"}}