{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NXG4RRMXPZWHM7CLEJJMFVLZ4B","short_pith_number":"pith:NXG4RRMX","schema_version":"1.0","canonical_sha256":"6dcdc8c5977e6c767c4b2252c2d579e06d1dac065a8ce19d7d3871d1cdeb7966","source":{"kind":"arxiv","id":"2112.05588","version":1},"attestation_state":"computed","paper":{"title":"Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bo Li, Dawn Song, Jialuo Chen, Jingyi Wang, Peng Cheng, Shouling Ji, Tinglan Peng, Xingjun Ma, Youcheng Sun","submitted_at":"2021-12-10T15:04:10Z","abstract_excerpt":"Deep learning (DL) models, especially those large-scale and high-performance ones, can be very costly to train, demanding a great amount of data and computational resources. Unauthorized reproduction of DL models can lead to copyright infringement and cause huge economic losses to model owners. Existing copyright protection techniques are mostly based on watermarking, which embeds an owner-specified watermark into the model. While being able to provide exact ownership verification, these techniques are 1) invasive, as they need to tamper with the training process, which may affect the utility "},"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":"2112.05588","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-12-10T15:04:10Z","cross_cats_sorted":[],"title_canon_sha256":"5b5107bea41c644158752bd03ac9bf1ba03a2010e920b807b7509ae44ceceafd","abstract_canon_sha256":"b39a857b22fa772ce3fb8821614d311c47b8f06ae324a143d98dce3a5772e203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:50.026685Z","signature_b64":"hK9lmNDIv8pb3l5lkiCbZumzjBCmzkt4cGQxZwP6FCEJxZOd23z9dmE6j28b/LRy+kgVid1zuVXipqKQfDxbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dcdc8c5977e6c767c4b2252c2d579e06d1dac065a8ce19d7d3871d1cdeb7966","last_reissued_at":"2026-07-05T03:39:50.026272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:50.026272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bo Li, Dawn Song, Jialuo Chen, Jingyi Wang, Peng Cheng, Shouling Ji, Tinglan Peng, Xingjun Ma, Youcheng Sun","submitted_at":"2021-12-10T15:04:10Z","abstract_excerpt":"Deep learning (DL) models, especially those large-scale and high-performance ones, can be very costly to train, demanding a great amount of data and computational resources. Unauthorized reproduction of DL models can lead to copyright infringement and cause huge economic losses to model owners. Existing copyright protection techniques are mostly based on watermarking, which embeds an owner-specified watermark into the model. While being able to provide exact ownership verification, these techniques are 1) invasive, as they need to tamper with the training process, which may affect the utility "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05588","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/2112.05588/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":"2112.05588","created_at":"2026-07-05T03:39:50.026331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.05588v1","created_at":"2026-07-05T03:39:50.026331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05588","created_at":"2026-07-05T03:39:50.026331+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXG4RRMXPZWH","created_at":"2026-07-05T03:39:50.026331+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXG4RRMXPZWHM7CL","created_at":"2026-07-05T03:39:50.026331+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXG4RRMX","created_at":"2026-07-05T03:39:50.026331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B","json":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B.json","graph_json":"https://pith.science/api/pith-number/NXG4RRMXPZWHM7CLEJJMFVLZ4B/graph.json","events_json":"https://pith.science/api/pith-number/NXG4RRMXPZWHM7CLEJJMFVLZ4B/events.json","paper":"https://pith.science/paper/NXG4RRMX"},"agent_actions":{"view_html":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B","download_json":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B.json","view_paper":"https://pith.science/paper/NXG4RRMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.05588&json=true","fetch_graph":"https://pith.science/api/pith-number/NXG4RRMXPZWHM7CLEJJMFVLZ4B/graph.json","fetch_events":"https://pith.science/api/pith-number/NXG4RRMXPZWHM7CLEJJMFVLZ4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B/action/storage_attestation","attest_author":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B/action/author_attestation","sign_citation":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B/action/citation_signature","submit_replication":"https://pith.science/pith/NXG4RRMXPZWHM7CLEJJMFVLZ4B/action/replication_record"}},"created_at":"2026-07-05T03:39:50.026331+00:00","updated_at":"2026-07-05T03:39:50.026331+00:00"}