{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G3TMBTVK37H4AI4IN7Y5CV73VW","short_pith_number":"pith:G3TMBTVK","schema_version":"1.0","canonical_sha256":"36e6c0ceaadfcfc023886ff1d157fbad827b000aadc66dc6af3a10cc8cb2f7ae","source":{"kind":"arxiv","id":"2507.14240","version":3},"attestation_state":"computed","paper":{"title":"HuggingGraph: Understanding the Supply Chain of LLM Ecosystem","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mohammad Shahedur Rahman, Peng Gao, Yuede Ji","submitted_at":"2025-07-17T17:34:13Z","abstract_excerpt":"Large language models (LLMs) leverage deep learning architectures to process and predict sequences of words, enabling them to perform a wide range of natural language processing tasks, such as translation, summarization, question answering, and content generation. As existing LLMs are often built from base models or other pre-trained models and use external datasets, they can inevitably inherit vulnerabilities, biases, or malicious components that exist in previous models or datasets. Therefore, it is critical to understand these components' origin and development process to detect potential r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.14240","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T17:34:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ab1ad52bf1e6c942a61a2daa1bf480359890349b5d5c70b24941bbceffe61d5","abstract_canon_sha256":"37c1dbad1d94b50828280294e86dbda261e3cf46d40b099c7c3dafdeaa2b1cea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:19.034494Z","signature_b64":"8enj8mgkAklazpFK2lBYZeJLjcVC5xV5POwNcR1NevBfsFTdO/g2BPx4ndN2Wg1NIidiIWyGYua/ngBGrmVqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e6c0ceaadfcfc023886ff1d157fbad827b000aadc66dc6af3a10cc8cb2f7ae","last_reissued_at":"2026-07-05T12:05:19.033864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:19.033864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HuggingGraph: Understanding the Supply Chain of LLM Ecosystem","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mohammad Shahedur Rahman, Peng Gao, Yuede Ji","submitted_at":"2025-07-17T17:34:13Z","abstract_excerpt":"Large language models (LLMs) leverage deep learning architectures to process and predict sequences of words, enabling them to perform a wide range of natural language processing tasks, such as translation, summarization, question answering, and content generation. As existing LLMs are often built from base models or other pre-trained models and use external datasets, they can inevitably inherit vulnerabilities, biases, or malicious components that exist in previous models or datasets. Therefore, it is critical to understand these components' origin and development process to detect potential r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14240","kind":"arxiv","version":3},"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/2507.14240/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.14240","created_at":"2026-07-05T12:05:19.033927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14240v3","created_at":"2026-07-05T12:05:19.033927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14240","created_at":"2026-07-05T12:05:19.033927+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3TMBTVK37H4","created_at":"2026-07-05T12:05:19.033927+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3TMBTVK37H4AI4I","created_at":"2026-07-05T12:05:19.033927+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3TMBTVK","created_at":"2026-07-05T12:05:19.033927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16902","citing_title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24496","citing_title":"LLM DNA: Tracing Model Evolution via Functional Representations","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW","json":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW.json","graph_json":"https://pith.science/api/pith-number/G3TMBTVK37H4AI4IN7Y5CV73VW/graph.json","events_json":"https://pith.science/api/pith-number/G3TMBTVK37H4AI4IN7Y5CV73VW/events.json","paper":"https://pith.science/paper/G3TMBTVK"},"agent_actions":{"view_html":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW","download_json":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW.json","view_paper":"https://pith.science/paper/G3TMBTVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14240&json=true","fetch_graph":"https://pith.science/api/pith-number/G3TMBTVK37H4AI4IN7Y5CV73VW/graph.json","fetch_events":"https://pith.science/api/pith-number/G3TMBTVK37H4AI4IN7Y5CV73VW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW/action/storage_attestation","attest_author":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW/action/author_attestation","sign_citation":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW/action/citation_signature","submit_replication":"https://pith.science/pith/G3TMBTVK37H4AI4IN7Y5CV73VW/action/replication_record"}},"created_at":"2026-07-05T12:05:19.033927+00:00","updated_at":"2026-07-05T12:05:19.033927+00:00"}