{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7L2QCRDTCF5GS6TCIJRGNUVMC4","short_pith_number":"pith:7L2QCRDT","canonical_record":{"source":{"id":"2407.13493","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-07-18T13:23:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"92140d34541f9744399eba99e28e3cedd398e00e4924eda7b65f0ccbe528cc82","abstract_canon_sha256":"d3688dee145af825199d4890d3b9c5a0f5110c13f60bb26147f989faf2f3e616"},"schema_version":"1.0"},"canonical_sha256":"faf5014473117a697a62426266d2ac170d124034d68b797c6f1d8375f7bfeed7","source":{"kind":"arxiv","id":"2407.13493","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13493","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13493v4","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13493","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"7L2QCRDTCF5G","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"7L2QCRDTCF5GS6TC","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"7L2QCRDT","created_at":"2026-07-05T10:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7L2QCRDTCF5GS6TCIJRGNUVMC4","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13493","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-07-18T13:23:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"92140d34541f9744399eba99e28e3cedd398e00e4924eda7b65f0ccbe528cc82","abstract_canon_sha256":"d3688dee145af825199d4890d3b9c5a0f5110c13f60bb26147f989faf2f3e616"},"schema_version":"1.0"},"canonical_sha256":"faf5014473117a697a62426266d2ac170d124034d68b797c6f1d8375f7bfeed7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:19.742217Z","signature_b64":"et0F/hHOCxBt/ggBks5g/W42DHvlZeNM/lPrJQCJhDBIzOJSoEFRrPqB2Nj2OuJxkqU0KMygveGy/a3KI8sHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faf5014473117a697a62426266d2ac170d124034d68b797c6f1d8375f7bfeed7","last_reissued_at":"2026-07-05T10:29:19.741272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:19.741272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13493","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N16fYG9ub/LoendHBcW8OTQvukFByjxU8qM4BWmwpXFNsjxBoI3U1YnH4+D9GILiKbktgvRDSv0ri8s/hQWpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:31:00.443103Z"},"content_sha256":"3915de6e5f24656a3fdb33a8e7c0bdd113826d0b02291d04783e405c6067892a","schema_version":"1.0","event_id":"sha256:3915de6e5f24656a3fdb33a8e7c0bdd113826d0b02291d04783e405c6067892a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7L2QCRDTCF5GS6TCIJRGNUVMC4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Claudia Cevenini, Giorgio Franceschelli, Mirco Musolesi","submitted_at":"2024-07-18T13:23:16Z","abstract_excerpt":"The training process of foundation models as for other classes of deep learning systems is based on minimizing the reconstruction error over a training set. For this reason, they are susceptible to the memorization and subsequent reproduction of training samples. In this paper, we introduce a training-as-compressing perspective, wherein the model's weights embody a compressed representation of the training data. From a copyright standpoint, this point of view implies that the weights can be considered a reproduction or, more likely, a derivative work of a potentially protected set of works. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13493","kind":"arxiv","version":4},"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/2407.13493/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":"2026-07-05T10:29:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFwLLgwvNqBONagyjn33F1cwlF7qcqx+fCfSiZ4xNneMIHzcAgyHs+iX38Kp1XZeI9qv8OuB0nLMKhpF4wZrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:31:00.443601Z"},"content_sha256":"b0474fd613e862ee8e537cda621fadc751a5dfb38984026cf2857dab39f0e3f9","schema_version":"1.0","event_id":"sha256:b0474fd613e862ee8e537cda621fadc751a5dfb38984026cf2857dab39f0e3f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4/bundle.json","state_url":"https://pith.science/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4/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":"2026-08-09T16:31:00Z","links":{"resolver":"https://pith.science/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4","bundle":"https://pith.science/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4/bundle.json","state":"https://pith.science/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7L2QCRDTCF5GS6TCIJRGNUVMC4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7L2QCRDTCF5GS6TCIJRGNUVMC4","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":"d3688dee145af825199d4890d3b9c5a0f5110c13f60bb26147f989faf2f3e616","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-07-18T13:23:16Z","title_canon_sha256":"92140d34541f9744399eba99e28e3cedd398e00e4924eda7b65f0ccbe528cc82"},"schema_version":"1.0","source":{"id":"2407.13493","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13493","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13493v4","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13493","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"7L2QCRDTCF5G","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"7L2QCRDTCF5GS6TC","created_at":"2026-07-05T10:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"7L2QCRDT","created_at":"2026-07-05T10:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:b0474fd613e862ee8e537cda621fadc751a5dfb38984026cf2857dab39f0e3f9","target":"graph","created_at":"2026-07-05T10:29:19Z","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/2407.13493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training process of foundation models as for other classes of deep learning systems is based on minimizing the reconstruction error over a training set. For this reason, they are susceptible to the memorization and subsequent reproduction of training samples. In this paper, we introduce a training-as-compressing perspective, wherein the model's weights embody a compressed representation of the training data. From a copyright standpoint, this point of view implies that the weights can be considered a reproduction or, more likely, a derivative work of a potentially protected set of works. We","authors_text":"Claudia Cevenini, Giorgio Franceschelli, Mirco Musolesi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-07-18T13:23:16Z","title":"Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13493","kind":"arxiv","version":4},"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":"sha256:3915de6e5f24656a3fdb33a8e7c0bdd113826d0b02291d04783e405c6067892a","target":"record","created_at":"2026-07-05T10:29:19Z","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":"d3688dee145af825199d4890d3b9c5a0f5110c13f60bb26147f989faf2f3e616","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-07-18T13:23:16Z","title_canon_sha256":"92140d34541f9744399eba99e28e3cedd398e00e4924eda7b65f0ccbe528cc82"},"schema_version":"1.0","source":{"id":"2407.13493","kind":"arxiv","version":4}},"canonical_sha256":"faf5014473117a697a62426266d2ac170d124034d68b797c6f1d8375f7bfeed7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faf5014473117a697a62426266d2ac170d124034d68b797c6f1d8375f7bfeed7","first_computed_at":"2026-07-05T10:29:19.741272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:19.741272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"et0F/hHOCxBt/ggBks5g/W42DHvlZeNM/lPrJQCJhDBIzOJSoEFRrPqB2Nj2OuJxkqU0KMygveGy/a3KI8sHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:19.742217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13493","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3915de6e5f24656a3fdb33a8e7c0bdd113826d0b02291d04783e405c6067892a","sha256:b0474fd613e862ee8e537cda621fadc751a5dfb38984026cf2857dab39f0e3f9"],"state_sha256":"f19290d2650217fa61feca1befdd232ecc98e260c138f9400037d3f01f967042"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKYjUCkYHYTbBXOC0q8jwbjH4z5Fv9jQzElofcRze1R6H/mp4L50YUNlCybVEiU9TLXeizUFSbJJ+TO3q89XCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:31:00.447916Z","bundle_sha256":"337ade913cfc71fc1f5da68f4211eb8b138e9fa05eaceb92ad2365b3a0d852e5"}}