{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MBJFCXOAGRG7REYZZTD5RDEG7W","short_pith_number":"pith:MBJFCXOA","canonical_record":{"source":{"id":"2306.09308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T17:42:48Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"8d2ca0e7adf01b625ae64230b19de5600a3e88057bc31e0aa4a03e9fd89b9e5e","abstract_canon_sha256":"659e8fd722e163785bf21657eac4d0da0f6406a8c11f7a882bd5d0b5c34c27c3"},"schema_version":"1.0"},"canonical_sha256":"6052515dc0344df89319ccc7d88c86fd99931d1c46273bdda14d5478ca6b96b8","source":{"kind":"arxiv","id":"2306.09308","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09308","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09308v1","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09308","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_12","alias_value":"MBJFCXOAGRG7","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_16","alias_value":"MBJFCXOAGRG7REYZ","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_8","alias_value":"MBJFCXOA","created_at":"2026-07-05T06:21:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MBJFCXOAGRG7REYZZTD5RDEG7W","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T17:42:48Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"8d2ca0e7adf01b625ae64230b19de5600a3e88057bc31e0aa4a03e9fd89b9e5e","abstract_canon_sha256":"659e8fd722e163785bf21657eac4d0da0f6406a8c11f7a882bd5d0b5c34c27c3"},"schema_version":"1.0"},"canonical_sha256":"6052515dc0344df89319ccc7d88c86fd99931d1c46273bdda14d5478ca6b96b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:10.861154Z","signature_b64":"hbOGaz8NNQQMRHQ7CVyc2u8jEi80HjZuQRKRR3IGhAbogKU19GcopZ9hOU0grUPPvoJCtTP7C5ebfmodvD4vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6052515dc0344df89319ccc7d88c86fd99931d1c46273bdda14d5478ca6b96b8","last_reissued_at":"2026-07-05T06:21:10.860813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:10.860813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09308","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":"2026-07-05T06:21:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M5MSSIqWt8fpuFqd/j5lCEWodafaWkb3BbsQYTJP3gc8jEKSCltL/KiMuZSMlmBCrv5IRaV0FyI1Kim217elAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:54:43.033441Z"},"content_sha256":"b48457bb527fa855d945478c6ccbad1dc71fdb6b09b9bbc1622c5440a3ef6421","schema_version":"1.0","event_id":"sha256:b48457bb527fa855d945478c6ccbad1dc71fdb6b09b9bbc1622c5440a3ef6421"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MBJFCXOAGRG7REYZZTD5RDEG7W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Ambrish Rawat, Gabriele Picco, Giulio Zizzo, Myles Foley, Taesung Lee, Yufang Hou","submitted_at":"2023-06-15T17:42:48Z","abstract_excerpt":"The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on various downstream applications. However, this leads to issues over violation of model licenses, model theft, and copyright infringement. Moreover, recent advances show that generative technology is capable of producing harmful content which exacerbates the problems of accountability within model supply chains. Thus, we need a method to investigate how a model wa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09308","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/2306.09308/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":"2026-07-05T06:21:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uoLElgSBYQTHzmZj7SobahL/hV3pjYhIEozQ8GLT7QCbK6OMQQGX8fFuQK21q+aamuDF8wUQBFSAQ9H7St+PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:54:43.034024Z"},"content_sha256":"b5375ddebde21f00db31609c95e8ff8b5d9b8d5a6391d3d478626f54cda8b99c","schema_version":"1.0","event_id":"sha256:b5375ddebde21f00db31609c95e8ff8b5d9b8d5a6391d3d478626f54cda8b99c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBJFCXOAGRG7REYZZTD5RDEG7W/bundle.json","state_url":"https://pith.science/pith/MBJFCXOAGRG7REYZZTD5RDEG7W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBJFCXOAGRG7REYZZTD5RDEG7W/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":"2026-08-09T22:54:43Z","links":{"resolver":"https://pith.science/pith/MBJFCXOAGRG7REYZZTD5RDEG7W","bundle":"https://pith.science/pith/MBJFCXOAGRG7REYZZTD5RDEG7W/bundle.json","state":"https://pith.science/pith/MBJFCXOAGRG7REYZZTD5RDEG7W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBJFCXOAGRG7REYZZTD5RDEG7W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MBJFCXOAGRG7REYZZTD5RDEG7W","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":"659e8fd722e163785bf21657eac4d0da0f6406a8c11f7a882bd5d0b5c34c27c3","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T17:42:48Z","title_canon_sha256":"8d2ca0e7adf01b625ae64230b19de5600a3e88057bc31e0aa4a03e9fd89b9e5e"},"schema_version":"1.0","source":{"id":"2306.09308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09308","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09308v1","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09308","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_12","alias_value":"MBJFCXOAGRG7","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_16","alias_value":"MBJFCXOAGRG7REYZ","created_at":"2026-07-05T06:21:10Z"},{"alias_kind":"pith_short_8","alias_value":"MBJFCXOA","created_at":"2026-07-05T06:21:10Z"}],"graph_snapshots":[{"event_id":"sha256:b5375ddebde21f00db31609c95e8ff8b5d9b8d5a6391d3d478626f54cda8b99c","target":"graph","created_at":"2026-07-05T06:21:10Z","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/2306.09308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on various downstream applications. However, this leads to issues over violation of model licenses, model theft, and copyright infringement. Moreover, recent advances show that generative technology is capable of producing harmful content which exacerbates the problems of accountability within model supply chains. Thus, we need a method to investigate how a model wa","authors_text":"Ambrish Rawat, Gabriele Picco, Giulio Zizzo, Myles Foley, Taesung Lee, Yufang Hou","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T17:42:48Z","title":"Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09308","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:b48457bb527fa855d945478c6ccbad1dc71fdb6b09b9bbc1622c5440a3ef6421","target":"record","created_at":"2026-07-05T06:21:10Z","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":"659e8fd722e163785bf21657eac4d0da0f6406a8c11f7a882bd5d0b5c34c27c3","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T17:42:48Z","title_canon_sha256":"8d2ca0e7adf01b625ae64230b19de5600a3e88057bc31e0aa4a03e9fd89b9e5e"},"schema_version":"1.0","source":{"id":"2306.09308","kind":"arxiv","version":1}},"canonical_sha256":"6052515dc0344df89319ccc7d88c86fd99931d1c46273bdda14d5478ca6b96b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6052515dc0344df89319ccc7d88c86fd99931d1c46273bdda14d5478ca6b96b8","first_computed_at":"2026-07-05T06:21:10.860813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:10.860813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hbOGaz8NNQQMRHQ7CVyc2u8jEi80HjZuQRKRR3IGhAbogKU19GcopZ9hOU0grUPPvoJCtTP7C5ebfmodvD4vCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:10.861154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b48457bb527fa855d945478c6ccbad1dc71fdb6b09b9bbc1622c5440a3ef6421","sha256:b5375ddebde21f00db31609c95e8ff8b5d9b8d5a6391d3d478626f54cda8b99c"],"state_sha256":"7912622a5a902338da020f113e8a815cc550ff859b22dce68cbe03c14b48ee2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USWNHjJXDlFICqwPcKs0Fe35NCj3R1u5azxsMByD739eboYvMSC1Ur3KlcFsTuu8lvCqRM0F8MmhYhLihyS+BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:54:43.039393Z","bundle_sha256":"03243b797cd41f3b8e433fb0c47c2b195179b73ac56c8c06a5cfba2304cf25a5"}}