{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3BBTSSM5JKMKZQNRZXQOXHOQDI","short_pith_number":"pith:3BBTSSM5","canonical_record":{"source":{"id":"2505.15501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T13:22:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"252655fc6c641d97453ef80fc4b52517764ff0ba5ba0be450e030218cf3deebb","abstract_canon_sha256":"75a5981c9dbb7c409c4076a26448232f6f72238d4c0cd47435cad9109b020ff3"},"schema_version":"1.0"},"canonical_sha256":"d84339499d4a98acc1b1cde0eb9dd01a37d5a3f852cd9af9850fdf3154fabf78","source":{"kind":"arxiv","id":"2505.15501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15501","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15501v1","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15501","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"3BBTSSM5JKMK","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"3BBTSSM5JKMKZQNR","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"3BBTSSM5","created_at":"2026-07-05T11:06:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3BBTSSM5JKMKZQNRZXQOXHOQDI","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T13:22:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"252655fc6c641d97453ef80fc4b52517764ff0ba5ba0be450e030218cf3deebb","abstract_canon_sha256":"75a5981c9dbb7c409c4076a26448232f6f72238d4c0cd47435cad9109b020ff3"},"schema_version":"1.0"},"canonical_sha256":"d84339499d4a98acc1b1cde0eb9dd01a37d5a3f852cd9af9850fdf3154fabf78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:46.820396Z","signature_b64":"nOFAi/QmD9/vhCy+wgdF1PfF3GQsh5cj7BuMVnO9jAPJKu7LrCm3eXWeQQyKicP1MkBwmJCCW9maxdVf5gppCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d84339499d4a98acc1b1cde0eb9dd01a37d5a3f852cd9af9850fdf3154fabf78","last_reissued_at":"2026-07-05T11:06:46.819926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:46.819926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15501","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":"2026-07-05T11:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kZAJq3Ia9PXdG5GAL8oqlE6J1VOhCjdjbXyB16yOT860psac9l0x6Wza0Eng52CSLLCs3WliH4BLhAw7M6uCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:28.899809Z"},"content_sha256":"1ffb85f447e7e0419517ddd8215ebea64c3ce7ab56ad0d6f73734078fbd3e757","schema_version":"1.0","event_id":"sha256:1ffb85f447e7e0419517ddd8215ebea64c3ce7ab56ad0d6f73734078fbd3e757"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3BBTSSM5JKMKZQNRZXQOXHOQDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Zugarini, Fabio Massimo Zanzotto, Federico Ranaldi, Leonardo Ranaldi","submitted_at":"2025-05-21T13:22:34Z","abstract_excerpt":"We introduce the concept of protoknowledge to formalize and measure how sequences of tokens encoding Knowledge Graphs are internalized during pretraining and utilized at inference time by Large Language Models (LLMs). Indeed, LLMs have demonstrated the ability to memorize vast amounts of token sequences during pretraining, and a central open question is how they leverage this memorization as reusable knowledge through generalization. We then categorize protoknowledge into lexical, hierarchical, and topological forms, varying on the type of knowledge that needs to be activated. We measure proto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15501","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/2505.15501/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":"2026-07-05T11:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DIeWpB+35eEMkGzj5ABBVUBNa/GRoCh+vZdUwr33pG/ZxpAgtLu4HDINqjrZ5HrTg4qhQHdEX5ZQU0KFaT5OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:28.900317Z"},"content_sha256":"12d4bdc8fbddeb3348f2393eb97761ce06fd370cc6ccba166195386cee8e78b3","schema_version":"1.0","event_id":"sha256:12d4bdc8fbddeb3348f2393eb97761ce06fd370cc6ccba166195386cee8e78b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI/bundle.json","state_url":"https://pith.science/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI/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":"2026-08-08T18:23:28Z","links":{"resolver":"https://pith.science/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI","bundle":"https://pith.science/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI/bundle.json","state":"https://pith.science/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BBTSSM5JKMKZQNRZXQOXHOQDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3BBTSSM5JKMKZQNRZXQOXHOQDI","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":"75a5981c9dbb7c409c4076a26448232f6f72238d4c0cd47435cad9109b020ff3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T13:22:34Z","title_canon_sha256":"252655fc6c641d97453ef80fc4b52517764ff0ba5ba0be450e030218cf3deebb"},"schema_version":"1.0","source":{"id":"2505.15501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15501","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15501v1","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15501","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"3BBTSSM5JKMK","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"3BBTSSM5JKMKZQNR","created_at":"2026-07-05T11:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"3BBTSSM5","created_at":"2026-07-05T11:06:46Z"}],"graph_snapshots":[{"event_id":"sha256:12d4bdc8fbddeb3348f2393eb97761ce06fd370cc6ccba166195386cee8e78b3","target":"graph","created_at":"2026-07-05T11:06:46Z","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/2505.15501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the concept of protoknowledge to formalize and measure how sequences of tokens encoding Knowledge Graphs are internalized during pretraining and utilized at inference time by Large Language Models (LLMs). Indeed, LLMs have demonstrated the ability to memorize vast amounts of token sequences during pretraining, and a central open question is how they leverage this memorization as reusable knowledge through generalization. We then categorize protoknowledge into lexical, hierarchical, and topological forms, varying on the type of knowledge that needs to be activated. We measure proto","authors_text":"Andrea Zugarini, Fabio Massimo Zanzotto, Federico Ranaldi, Leonardo Ranaldi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T13:22:34Z","title":"Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15501","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":"sha256:1ffb85f447e7e0419517ddd8215ebea64c3ce7ab56ad0d6f73734078fbd3e757","target":"record","created_at":"2026-07-05T11:06:46Z","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":"75a5981c9dbb7c409c4076a26448232f6f72238d4c0cd47435cad9109b020ff3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T13:22:34Z","title_canon_sha256":"252655fc6c641d97453ef80fc4b52517764ff0ba5ba0be450e030218cf3deebb"},"schema_version":"1.0","source":{"id":"2505.15501","kind":"arxiv","version":1}},"canonical_sha256":"d84339499d4a98acc1b1cde0eb9dd01a37d5a3f852cd9af9850fdf3154fabf78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d84339499d4a98acc1b1cde0eb9dd01a37d5a3f852cd9af9850fdf3154fabf78","first_computed_at":"2026-07-05T11:06:46.819926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:46.819926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nOFAi/QmD9/vhCy+wgdF1PfF3GQsh5cj7BuMVnO9jAPJKu7LrCm3eXWeQQyKicP1MkBwmJCCW9maxdVf5gppCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:46.820396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ffb85f447e7e0419517ddd8215ebea64c3ce7ab56ad0d6f73734078fbd3e757","sha256:12d4bdc8fbddeb3348f2393eb97761ce06fd370cc6ccba166195386cee8e78b3"],"state_sha256":"c5fb45c8f8f1a40cb57e16d9eb527d1a556bd6c073c4e52607fe8185ccf6cf38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yqxQdhP/elaKEBM70js0xaJxiZK/PbLIs58gXoBljnN1PfQf1jXR4S2swbUFrE9EmGTwFeNlpccp4xIB6k5rDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:23:28.905262Z","bundle_sha256":"92b731cb78735a18b499e277552d892d7bfa934eb2fcce80ffe3efb27ac30ce2"}}