{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FWXMNBXMKW3JQCY6SHKM2L6ZEW","short_pith_number":"pith:FWXMNBXM","canonical_record":{"source":{"id":"2607.24192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2026-07-27T09:12:00Z","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"title_canon_sha256":"a5c6575ba80124a3cabb590c69b5c7904bacb0184bbdbdfcfa09f21404fca7de","abstract_canon_sha256":"fa48b5d00c68371f6c25266b7da0e428aa01a126b27a417a83f154fe0c661f54"},"schema_version":"1.0"},"canonical_sha256":"2daec686ec55b6980b1e91d4cd2fd9258e0fa8f4533aad1af626b4ead3dc14da","source":{"kind":"arxiv","id":"2607.24192","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24192","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24192v1","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24192","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"FWXMNBXMKW3J","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"FWXMNBXMKW3JQCY6","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"FWXMNBXM","created_at":"2026-07-28T02:23:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FWXMNBXMKW3JQCY6SHKM2L6ZEW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2026-07-27T09:12:00Z","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"title_canon_sha256":"a5c6575ba80124a3cabb590c69b5c7904bacb0184bbdbdfcfa09f21404fca7de","abstract_canon_sha256":"fa48b5d00c68371f6c25266b7da0e428aa01a126b27a417a83f154fe0c661f54"},"schema_version":"1.0"},"canonical_sha256":"2daec686ec55b6980b1e91d4cd2fd9258e0fa8f4533aad1af626b4ead3dc14da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:50.126776Z","signature_b64":"4AVQaRbZhpbFAQYZcYPP/oYn3bGnpNoblg8MEw4/EZomv3IndO0C5ebF1TnV47nVAQ6bhSUT1RDcm2cfEUAwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2daec686ec55b6980b1e91d4cd2fd9258e0fa8f4533aad1af626b4ead3dc14da","last_reissued_at":"2026-07-28T02:23:50.125836Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:50.125836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24192","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":"2026-07-28T02:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aass/MdHq9c+a2gLk3WTHTnxPQHYBxY1fduroQxWakF+4+lxsSwUA4YQ+pDHmVtpUbAIryLfI4wDYTSPBvKoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:57:43.880044Z"},"content_sha256":"88b73f0957af37980463606f6b9e71351380cb3eb3292f4e003cdcff5aaeadf1","schema_version":"1.0","event_id":"sha256:88b73f0957af37980463606f6b9e71351380cb3eb3292f4e003cdcff5aaeadf1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FWXMNBXMKW3JQCY6SHKM2L6ZEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-based Source Code Compression via Thresholded Symbol Ranking","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Angelo Nardone, Paolo Ferragina","submitted_at":"2026-07-27T09:12:00Z","abstract_excerpt":"We study the problem of lossless compression of source code, motivated by the storage demands of large-scale software archives, such as Software Heritage (https://www.softwareheritage.org/). General-purpose compressors (e.g., zstd, bzip2) offer a good trade-off between compression ratio and speed, but fail to exploit all special regularities inherent in source code. Recent approaches leverage Large Language Models (LLMs) within Shannon's symbol-ranking framework, relying on a scheme in which the predicted rank can grow arbitrarily. While effective at reducing space, this setting incurs signifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24192","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/2607.24192/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":"2026-07-28T02:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ioFVdn9LUnshFrBd9Rib16olkpR0ftzqvJOOZMG6LxbLGLrajRyoxPsysE1cTR/HQdHRE0hKS4MaFSaEy9MMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T10:57:43.880543Z"},"content_sha256":"47a1c7b4d296e78d9e77b5ec1a2d8b4ea6186461a61b33380fdafd656a0fbed9","schema_version":"1.0","event_id":"sha256:47a1c7b4d296e78d9e77b5ec1a2d8b4ea6186461a61b33380fdafd656a0fbed9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW/bundle.json","state_url":"https://pith.science/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW/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":"2026-08-22T10:57:43Z","links":{"resolver":"https://pith.science/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW","bundle":"https://pith.science/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW/bundle.json","state":"https://pith.science/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWXMNBXMKW3JQCY6SHKM2L6ZEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FWXMNBXMKW3JQCY6SHKM2L6ZEW","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":"fa48b5d00c68371f6c25266b7da0e428aa01a126b27a417a83f154fe0c661f54","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2026-07-27T09:12:00Z","title_canon_sha256":"a5c6575ba80124a3cabb590c69b5c7904bacb0184bbdbdfcfa09f21404fca7de"},"schema_version":"1.0","source":{"id":"2607.24192","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24192","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24192v1","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24192","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"FWXMNBXMKW3J","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"FWXMNBXMKW3JQCY6","created_at":"2026-07-28T02:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"FWXMNBXM","created_at":"2026-07-28T02:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:47a1c7b4d296e78d9e77b5ec1a2d8b4ea6186461a61b33380fdafd656a0fbed9","target":"graph","created_at":"2026-07-28T02:23:50Z","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/2607.24192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of lossless compression of source code, motivated by the storage demands of large-scale software archives, such as Software Heritage (https://www.softwareheritage.org/). General-purpose compressors (e.g., zstd, bzip2) offer a good trade-off between compression ratio and speed, but fail to exploit all special regularities inherent in source code. Recent approaches leverage Large Language Models (LLMs) within Shannon's symbol-ranking framework, relying on a scheme in which the predicted rank can grow arbitrarily. While effective at reducing space, this setting incurs signifi","authors_text":"Angelo Nardone, Paolo Ferragina","cross_cats":["cs.CL","cs.LG","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2026-07-27T09:12:00Z","title":"LLM-based Source Code Compression via Thresholded Symbol Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24192","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":"sha256:88b73f0957af37980463606f6b9e71351380cb3eb3292f4e003cdcff5aaeadf1","target":"record","created_at":"2026-07-28T02:23:50Z","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":"fa48b5d00c68371f6c25266b7da0e428aa01a126b27a417a83f154fe0c661f54","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IT","submitted_at":"2026-07-27T09:12:00Z","title_canon_sha256":"a5c6575ba80124a3cabb590c69b5c7904bacb0184bbdbdfcfa09f21404fca7de"},"schema_version":"1.0","source":{"id":"2607.24192","kind":"arxiv","version":1}},"canonical_sha256":"2daec686ec55b6980b1e91d4cd2fd9258e0fa8f4533aad1af626b4ead3dc14da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2daec686ec55b6980b1e91d4cd2fd9258e0fa8f4533aad1af626b4ead3dc14da","first_computed_at":"2026-07-28T02:23:50.125836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:23:50.125836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4AVQaRbZhpbFAQYZcYPP/oYn3bGnpNoblg8MEw4/EZomv3IndO0C5ebF1TnV47nVAQ6bhSUT1RDcm2cfEUAwDg==","signature_status":"signed_v1","signed_at":"2026-07-28T02:23:50.126776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24192","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88b73f0957af37980463606f6b9e71351380cb3eb3292f4e003cdcff5aaeadf1","sha256:47a1c7b4d296e78d9e77b5ec1a2d8b4ea6186461a61b33380fdafd656a0fbed9"],"state_sha256":"57d7edfbcdbd9d814dbaef611b67168a3130ffd1a65683e847d5fa12b982391f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cr7l/YvQ1lWxYmBb5q06ROlJijLzJ1jMfw8ZHcssGKwFH4fu6X27xSE8aToC5TNRpWm7IAs3iSb7UFB9DW/wDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T10:57:43.884986Z","bundle_sha256":"c63ad8dc40e15ea41e56a1d7fceb39a4d6b3c8bb05fb6f444001c9a31b5645a8"}}