{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BPCJOW4ORX2IVHEP3IZ2OZCYLQ","short_pith_number":"pith:BPCJOW4O","schema_version":"1.0","canonical_sha256":"0bc4975b8e8df48a9c8fda33a764585c239713d89b3b6760e89f9915dadfa7eb","source":{"kind":"arxiv","id":"2507.01204","version":2},"attestation_state":"computed","paper":{"title":"LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"eess.IV","authors_text":"Deniz G\\\"und\\\"uz, Gongpu Chen, Haotian Wu, Pier Luigi Dragotti","submitted_at":"2025-07-01T21:48:16Z","abstract_excerpt":"We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted image compression, achieving rate-distortion (RD) performance comparable to trained networks. This hypothesis leads to a new paradigm for image compression by encoding image statistics into the network substructure. Building on this hypothesis, we propose LotteryCodec, which overfits a binary mask to an individual image, leveraging an over-parameterized and randomly initialized network shared by the encoder and the d"},"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":"2507.01204","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-07-01T21:48:16Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"07e97bdfae1499fa8851046a11012b8658b5df280775401a5ec13f583d69d8bc","abstract_canon_sha256":"bdc418434a323ea4a8487bd133a44fb7e0e86d96d7a21c5d6f4ce5d018bfa38f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:37.191895Z","signature_b64":"bFjokIq+pwqW3G32LWoCS/jYoUGOUChpLC+aY6ImtzhEP+BaSGHrVQL2h2nvEFH14Prcv4gUAV4i0cCcfLjeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bc4975b8e8df48a9c8fda33a764585c239713d89b3b6760e89f9915dadfa7eb","last_reissued_at":"2026-07-05T12:04:37.191389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:37.191389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"eess.IV","authors_text":"Deniz G\\\"und\\\"uz, Gongpu Chen, Haotian Wu, Pier Luigi Dragotti","submitted_at":"2025-07-01T21:48:16Z","abstract_excerpt":"We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted image compression, achieving rate-distortion (RD) performance comparable to trained networks. This hypothesis leads to a new paradigm for image compression by encoding image statistics into the network substructure. Building on this hypothesis, we propose LotteryCodec, which overfits a binary mask to an individual image, leveraging an over-parameterized and randomly initialized network shared by the encoder and the d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01204","kind":"arxiv","version":2},"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/2507.01204/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":"2507.01204","created_at":"2026-07-05T12:04:37.191451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01204v2","created_at":"2026-07-05T12:04:37.191451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01204","created_at":"2026-07-05T12:04:37.191451+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPCJOW4ORX2I","created_at":"2026-07-05T12:04:37.191451+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPCJOW4ORX2IVHEP","created_at":"2026-07-05T12:04:37.191451+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPCJOW4O","created_at":"2026-07-05T12:04:37.191451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.10433","citing_title":"Implicit Neural Compression of Point Clouds","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02726","citing_title":"Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ","json":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ.json","graph_json":"https://pith.science/api/pith-number/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/graph.json","events_json":"https://pith.science/api/pith-number/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/events.json","paper":"https://pith.science/paper/BPCJOW4O"},"agent_actions":{"view_html":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ","download_json":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ.json","view_paper":"https://pith.science/paper/BPCJOW4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01204&json=true","fetch_graph":"https://pith.science/api/pith-number/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/action/storage_attestation","attest_author":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/action/author_attestation","sign_citation":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/action/citation_signature","submit_replication":"https://pith.science/pith/BPCJOW4ORX2IVHEP3IZ2OZCYLQ/action/replication_record"}},"created_at":"2026-07-05T12:04:37.191451+00:00","updated_at":"2026-07-05T12:04:37.191451+00:00"}