{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EBBZXQZERKMY6ND4XQLOP4H45U","short_pith_number":"pith:EBBZXQZE","canonical_record":{"source":{"id":"2506.05672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T01:34:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cf1b47a8d76060ff25e8f6df2d69f8bbe5f9c07462d189e337c0aa2cee3438ae","abstract_canon_sha256":"c4e1a8cc5707f0f070aa68ea0ab7618d82d4ddf729dde5b11df39c52b7f9de99"},"schema_version":"1.0"},"canonical_sha256":"20439bc3248a998f347cbc16e7f0fced1fe6297b58b97559a14fe86a886fbf77","source":{"kind":"arxiv","id":"2506.05672","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05672","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05672v1","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05672","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"EBBZXQZERKMY","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"EBBZXQZERKMY6ND4","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"EBBZXQZE","created_at":"2026-07-05T11:17:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EBBZXQZERKMY6ND4XQLOP4H45U","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T01:34:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cf1b47a8d76060ff25e8f6df2d69f8bbe5f9c07462d189e337c0aa2cee3438ae","abstract_canon_sha256":"c4e1a8cc5707f0f070aa68ea0ab7618d82d4ddf729dde5b11df39c52b7f9de99"},"schema_version":"1.0"},"canonical_sha256":"20439bc3248a998f347cbc16e7f0fced1fe6297b58b97559a14fe86a886fbf77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:07.843834Z","signature_b64":"3QxKYgciUI2/6o+zGJOmpciNFAa+zWu6a56v4AEnNqE2i9F7otdsbUNtGrohwEWwunsaB1vRlAHCLvLJphCLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20439bc3248a998f347cbc16e7f0fced1fe6297b58b97559a14fe86a886fbf77","last_reissued_at":"2026-07-05T11:17:07.843342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:07.843342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05672","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":"2026-07-05T11:17:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BBP7brSnL81Cye4SMYDZVrmFsXBnlDFC2CLWX+vjWXIADGeivVGS9dgQ4sQDD2g5oDwF9qbo3dFoO6L0D6xTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:23:08.460296Z"},"content_sha256":"61e0d7ee5694523ab4d33dd7640339c3dc0048ef44201081de73eef7b4a17617","schema_version":"1.0","event_id":"sha256:61e0d7ee5694523ab4d33dd7640339c3dc0048ef44201081de73eef7b4a17617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EBBZXQZERKMY6ND4XQLOP4H45U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextually Guided Transformers via Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrey Zhmoginov, Jihwan Lee, Mark Sandler, Max Vladymyrov","submitted_at":"2025-06-06T01:34:39Z","abstract_excerpt":"Large Language Models (LLMs) based on Transformers excel at text processing, but their reliance on prompts for specialized behavior introduces computational overhead. We propose a modification to a Transformer architecture that eliminates the need for explicit prompts by learning to encode context into the model's weights. Our Contextually Guided Transformer (CGT) model maintains a contextual summary at each sequence position, allowing it to update the weights on the fly based on the preceding context. This approach enables the model to self-specialize, effectively creating a tailored model fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05672","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/2506.05672/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":"2026-07-05T11:17:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ghcehwWE/tDDcV/TNQk+ajomUz3QA9nVySGcCjcUbYKhPrgoS/zGvxl8xlRs5ShWsUhKRtaa+Vkbu0g7xU8TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:23:08.461200Z"},"content_sha256":"be09ea07c61d54a8ae31de8f296bcd5f0a156384aa5586e6cf27b1f2f1fc574c","schema_version":"1.0","event_id":"sha256:be09ea07c61d54a8ae31de8f296bcd5f0a156384aa5586e6cf27b1f2f1fc574c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBBZXQZERKMY6ND4XQLOP4H45U/bundle.json","state_url":"https://pith.science/pith/EBBZXQZERKMY6ND4XQLOP4H45U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBBZXQZERKMY6ND4XQLOP4H45U/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":"2026-08-09T01:23:08Z","links":{"resolver":"https://pith.science/pith/EBBZXQZERKMY6ND4XQLOP4H45U","bundle":"https://pith.science/pith/EBBZXQZERKMY6ND4XQLOP4H45U/bundle.json","state":"https://pith.science/pith/EBBZXQZERKMY6ND4XQLOP4H45U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBBZXQZERKMY6ND4XQLOP4H45U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EBBZXQZERKMY6ND4XQLOP4H45U","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":"c4e1a8cc5707f0f070aa68ea0ab7618d82d4ddf729dde5b11df39c52b7f9de99","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T01:34:39Z","title_canon_sha256":"cf1b47a8d76060ff25e8f6df2d69f8bbe5f9c07462d189e337c0aa2cee3438ae"},"schema_version":"1.0","source":{"id":"2506.05672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05672","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05672v1","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05672","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"EBBZXQZERKMY","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"EBBZXQZERKMY6ND4","created_at":"2026-07-05T11:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"EBBZXQZE","created_at":"2026-07-05T11:17:07Z"}],"graph_snapshots":[{"event_id":"sha256:be09ea07c61d54a8ae31de8f296bcd5f0a156384aa5586e6cf27b1f2f1fc574c","target":"graph","created_at":"2026-07-05T11:17:07Z","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/2506.05672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) based on Transformers excel at text processing, but their reliance on prompts for specialized behavior introduces computational overhead. We propose a modification to a Transformer architecture that eliminates the need for explicit prompts by learning to encode context into the model's weights. Our Contextually Guided Transformer (CGT) model maintains a contextual summary at each sequence position, allowing it to update the weights on the fly based on the preceding context. This approach enables the model to self-specialize, effectively creating a tailored model fo","authors_text":"Andrey Zhmoginov, Jihwan Lee, Mark Sandler, Max Vladymyrov","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T01:34:39Z","title":"Contextually Guided Transformers via Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05672","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":"sha256:61e0d7ee5694523ab4d33dd7640339c3dc0048ef44201081de73eef7b4a17617","target":"record","created_at":"2026-07-05T11:17:07Z","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":"c4e1a8cc5707f0f070aa68ea0ab7618d82d4ddf729dde5b11df39c52b7f9de99","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T01:34:39Z","title_canon_sha256":"cf1b47a8d76060ff25e8f6df2d69f8bbe5f9c07462d189e337c0aa2cee3438ae"},"schema_version":"1.0","source":{"id":"2506.05672","kind":"arxiv","version":1}},"canonical_sha256":"20439bc3248a998f347cbc16e7f0fced1fe6297b58b97559a14fe86a886fbf77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20439bc3248a998f347cbc16e7f0fced1fe6297b58b97559a14fe86a886fbf77","first_computed_at":"2026-07-05T11:17:07.843342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:07.843342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3QxKYgciUI2/6o+zGJOmpciNFAa+zWu6a56v4AEnNqE2i9F7otdsbUNtGrohwEWwunsaB1vRlAHCLvLJphCLBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:07.843834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61e0d7ee5694523ab4d33dd7640339c3dc0048ef44201081de73eef7b4a17617","sha256:be09ea07c61d54a8ae31de8f296bcd5f0a156384aa5586e6cf27b1f2f1fc574c"],"state_sha256":"b5686f4c3569789e0e8b75b906d71e3809fd0a9768d1dedafff357574011d6a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqH09vJ7o6ZWFQz7zSdY6Nv73L6nhYacYsv/FqjrbBhw8VASxiW+5cwS0LSKjimEanGZCjGFJZev0FC7M2zpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:23:08.466144Z","bundle_sha256":"32fa34d32000a40ed3868a2aae951688bddcb1970538b24e79e31543b92f1b3d"}}