{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2AU2V5GF3XQRL54AULCN5UKDVK","short_pith_number":"pith:2AU2V5GF","canonical_record":{"source":{"id":"2412.18621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"cea72e089a9e05e9e7f00f5d9c56e16d77bf4406430d30637c9c9b417be17c56","abstract_canon_sha256":"cbdc4f8bc9cd9b1b048d2cd758067d3520b5de29f44a740a097bd7546840f744"},"schema_version":"1.0"},"canonical_sha256":"d029aaf4c5dde115f780a2c4ded143aabddd7b1061e47845b98ed5cb52ec4a8f","source":{"kind":"arxiv","id":"2412.18621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18621","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18621v1","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18621","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"2AU2V5GF3XQR","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"2AU2V5GF3XQRL54A","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"2AU2V5GF","created_at":"2026-07-05T10:12:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2AU2V5GF3XQRL54AULCN5UKDVK","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"cea72e089a9e05e9e7f00f5d9c56e16d77bf4406430d30637c9c9b417be17c56","abstract_canon_sha256":"cbdc4f8bc9cd9b1b048d2cd758067d3520b5de29f44a740a097bd7546840f744"},"schema_version":"1.0"},"canonical_sha256":"d029aaf4c5dde115f780a2c4ded143aabddd7b1061e47845b98ed5cb52ec4a8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:03.035184Z","signature_b64":"pUTE8QaMiRzVOPZ9cSTH13myH7rRFTUBoDmOslja9z+bo1C7tyIsr/Qlk7gYZ3qwMopNIhs6VXVQBVpvQN7DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d029aaf4c5dde115f780a2c4ded143aabddd7b1061e47845b98ed5cb52ec4a8f","last_reissued_at":"2026-07-05T10:12:03.034701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:03.034701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18621","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":"2026-07-05T10:12:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+7K7e6dUbK6Fla51iPNuYu8qoylvlr9ATV+ZxJBVvCRlQtuFfeZBMFtPdVgnqKBnCQCTSwN3TNG2FOYcz4dCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:09:47.380461Z"},"content_sha256":"c5503084fa74ca6e1ae829c81f53347966ca0879b7bde26a6c4c76af1199d121","schema_version":"1.0","event_id":"sha256:c5503084fa74ca6e1ae829c81f53347966ca0879b7bde26a6c4c76af1199d121"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2AU2V5GF3XQRL54AULCN5UKDVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyao Dou","submitted_at":"2024-12-16T20:01:06Z","abstract_excerpt":"Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In a potential real-world scenario, model owners may need to continuously address copyright infringement in order to address requests for content removal that emerge at different time points. One potential way of addressing this is via sequential unlearning, where copyrighted content is removed sequentially as new requests arise. Despite its practical relevance, sequential unlearning in the con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18621","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/2412.18621/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":"2026-07-05T10:12:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"59i60dL5FUt4D+0ijRhN8IQEhNzaxqziRerdmgfromqToSK6cXVbUaNkKxHfUj/ydCn/5nHQciYX5+N/fE0pDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:09:47.380845Z"},"content_sha256":"531a5240561a90a97618767e65a6990bafd8cee29307f00853180f13ad9663f4","schema_version":"1.0","event_id":"sha256:531a5240561a90a97618767e65a6990bafd8cee29307f00853180f13ad9663f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2AU2V5GF3XQRL54AULCN5UKDVK/bundle.json","state_url":"https://pith.science/pith/2AU2V5GF3XQRL54AULCN5UKDVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2AU2V5GF3XQRL54AULCN5UKDVK/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":"2026-08-19T23:09:47Z","links":{"resolver":"https://pith.science/pith/2AU2V5GF3XQRL54AULCN5UKDVK","bundle":"https://pith.science/pith/2AU2V5GF3XQRL54AULCN5UKDVK/bundle.json","state":"https://pith.science/pith/2AU2V5GF3XQRL54AULCN5UKDVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2AU2V5GF3XQRL54AULCN5UKDVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2AU2V5GF3XQRL54AULCN5UKDVK","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":"cbdc4f8bc9cd9b1b048d2cd758067d3520b5de29f44a740a097bd7546840f744","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:01:06Z","title_canon_sha256":"cea72e089a9e05e9e7f00f5d9c56e16d77bf4406430d30637c9c9b417be17c56"},"schema_version":"1.0","source":{"id":"2412.18621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18621","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18621v1","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18621","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"2AU2V5GF3XQR","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"2AU2V5GF3XQRL54A","created_at":"2026-07-05T10:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"2AU2V5GF","created_at":"2026-07-05T10:12:03Z"}],"graph_snapshots":[{"event_id":"sha256:531a5240561a90a97618767e65a6990bafd8cee29307f00853180f13ad9663f4","target":"graph","created_at":"2026-07-05T10:12:03Z","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/2412.18621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In a potential real-world scenario, model owners may need to continuously address copyright infringement in order to address requests for content removal that emerge at different time points. One potential way of addressing this is via sequential unlearning, where copyrighted content is removed sequentially as new requests arise. Despite its practical relevance, sequential unlearning in the con","authors_text":"Guangyao Dou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:01:06Z","title":"Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18621","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:c5503084fa74ca6e1ae829c81f53347966ca0879b7bde26a6c4c76af1199d121","target":"record","created_at":"2026-07-05T10:12:03Z","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":"cbdc4f8bc9cd9b1b048d2cd758067d3520b5de29f44a740a097bd7546840f744","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:01:06Z","title_canon_sha256":"cea72e089a9e05e9e7f00f5d9c56e16d77bf4406430d30637c9c9b417be17c56"},"schema_version":"1.0","source":{"id":"2412.18621","kind":"arxiv","version":1}},"canonical_sha256":"d029aaf4c5dde115f780a2c4ded143aabddd7b1061e47845b98ed5cb52ec4a8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d029aaf4c5dde115f780a2c4ded143aabddd7b1061e47845b98ed5cb52ec4a8f","first_computed_at":"2026-07-05T10:12:03.034701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:03.034701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pUTE8QaMiRzVOPZ9cSTH13myH7rRFTUBoDmOslja9z+bo1C7tyIsr/Qlk7gYZ3qwMopNIhs6VXVQBVpvQN7DBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:03.035184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5503084fa74ca6e1ae829c81f53347966ca0879b7bde26a6c4c76af1199d121","sha256:531a5240561a90a97618767e65a6990bafd8cee29307f00853180f13ad9663f4"],"state_sha256":"cf2d8d0de47dc7d972688d18f52c26701e0c26543b304fb0ed4e7a61c7333810"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pxadIDuG0isodl1MO4NIV5CGMJpDh9zyBZzT5Rh+UqiGq3VkNF4LJS3eRVSYHLGzJFsdiHKP0KLshf7k8mBiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:09:47.384472Z","bundle_sha256":"35b0e044b67f05100a1247485061a25eb4757f1e51b0e1c1375ee9dda943e03d"}}