{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U2DWKK5BQ3AALHBSTR2QIHMGWH","short_pith_number":"pith:U2DWKK5B","canonical_record":{"source":{"id":"2411.09816","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T21:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"9e519a3233ea6c1d5e15c1fedd2c3d4c3d81dd134d85d0185b52577faf9d7615","abstract_canon_sha256":"d04bbf5ab56c731722496f53eca9bb5c92f461be13d65a20b2199c9327b8ad63"},"schema_version":"1.0"},"canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","source":{"kind":"arxiv","id":"2411.09816","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09816","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09816v4","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09816","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"U2DWKK5BQ3AA","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"U2DWKK5BQ3AALHBS","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"U2DWKK5B","created_at":"2026-05-26T01:03:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U2DWKK5BQ3AALHBSTR2QIHMGWH","target":"record","payload":{"canonical_record":{"source":{"id":"2411.09816","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T21:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"9e519a3233ea6c1d5e15c1fedd2c3d4c3d81dd134d85d0185b52577faf9d7615","abstract_canon_sha256":"d04bbf5ab56c731722496f53eca9bb5c92f461be13d65a20b2199c9327b8ad63"},"schema_version":"1.0"},"canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:09.641090Z","signature_b64":"qWVbdk2RRxkdA2XLXEfMmDRNbF00oL06vYWxc55GpFQMibb6Gs75WwGRmmSAfQEDrSua8Zb6lvEtbmGgij70Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","last_reissued_at":"2026-05-26T01:03:09.640206Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:09.640206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.09816","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":"2026-05-26T01:03:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k9xjpKQwIpSQjQHYeGJIZEazSG86m6HzyJ6OFfGCWCZu9OSTqiz/yTbddGB1MinW9xnB3SDxrhoYV0OSKlsQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:18:02.884960Z"},"content_sha256":"4ff2e46f43baa333387877cfe7e065a0b1ae8e848c57965d870b4ca529f4bcb1","schema_version":"1.0","event_id":"sha256:4ff2e46f43baa333387877cfe7e065a0b1ae8e848c57965d870b4ca529f4bcb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U2DWKK5BQ3AALHBSTR2QIHMGWH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cem \\\"Uy\\\"uk, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou","submitted_at":"2024-11-14T21:29:58Z","abstract_excerpt":"Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively unexplored for transformer models. In this paper, we introduce Fine-grained Parameter Sharing (FiPS), a unified framework for compressing transformer Multi-Layer Perceptrons (MLPs) that combines cross-block parameter sharing, low-rank factorization, and sparsity in a single optimization. FiPS concatenates MLP weight matrices across a group of transformer blocks a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09816","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/2411.09816/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":"2026-05-26T01:03:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BNbrXjBgyU4Lo5Oglz6f4NWykfxlweJM5r3EAcI2Lt1OF4hHvyheRk3Aq48Ksk1iFStHnsfmr5PqL2zcgoA9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:18:02.885832Z"},"content_sha256":"6eae4c6e3010c96cb72a7e9e99de2b9684d2d8f9004da7581975681f143bd91e","schema_version":"1.0","event_id":"sha256:6eae4c6e3010c96cb72a7e9e99de2b9684d2d8f9004da7581975681f143bd91e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/bundle.json","state_url":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/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":"2026-08-08T18:18:02Z","links":{"resolver":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH","bundle":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/bundle.json","state":"https://pith.science/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U2DWKK5BQ3AALHBSTR2QIHMGWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U2DWKK5BQ3AALHBSTR2QIHMGWH","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":"d04bbf5ab56c731722496f53eca9bb5c92f461be13d65a20b2199c9327b8ad63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T21:29:58Z","title_canon_sha256":"9e519a3233ea6c1d5e15c1fedd2c3d4c3d81dd134d85d0185b52577faf9d7615"},"schema_version":"1.0","source":{"id":"2411.09816","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09816","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09816v4","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09816","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"U2DWKK5BQ3AA","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"U2DWKK5BQ3AALHBS","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"U2DWKK5B","created_at":"2026-05-26T01:03:09Z"}],"graph_snapshots":[{"event_id":"sha256:6eae4c6e3010c96cb72a7e9e99de2b9684d2d8f9004da7581975681f143bd91e","target":"graph","created_at":"2026-05-26T01:03:09Z","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/2411.09816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively unexplored for transformer models. In this paper, we introduce Fine-grained Parameter Sharing (FiPS), a unified framework for compressing transformer Multi-Layer Perceptrons (MLPs) that combines cross-block parameter sharing, low-rank factorization, and sparsity in a single optimization. FiPS concatenates MLP weight matrices across a group of transformer blocks a","authors_text":"Cem \\\"Uy\\\"uk, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T21:29:58Z","title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09816","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":"sha256:4ff2e46f43baa333387877cfe7e065a0b1ae8e848c57965d870b4ca529f4bcb1","target":"record","created_at":"2026-05-26T01:03:09Z","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":"d04bbf5ab56c731722496f53eca9bb5c92f461be13d65a20b2199c9327b8ad63","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T21:29:58Z","title_canon_sha256":"9e519a3233ea6c1d5e15c1fedd2c3d4c3d81dd134d85d0185b52577faf9d7615"},"schema_version":"1.0","source":{"id":"2411.09816","kind":"arxiv","version":4}},"canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a687652ba186c0059c329c75041d86b1d5a66e1049e224c0798872ba4969b9f2","first_computed_at":"2026-05-26T01:03:09.640206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:09.640206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qWVbdk2RRxkdA2XLXEfMmDRNbF00oL06vYWxc55GpFQMibb6Gs75WwGRmmSAfQEDrSua8Zb6lvEtbmGgij70Cg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:09.641090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09816","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ff2e46f43baa333387877cfe7e065a0b1ae8e848c57965d870b4ca529f4bcb1","sha256:6eae4c6e3010c96cb72a7e9e99de2b9684d2d8f9004da7581975681f143bd91e"],"state_sha256":"df00cf8f718675ccf9e2bbc469075aac0711804826a665cf8ff9b01f7d04e968"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WLIQFgd4YmkdBILiC5TIK7U+VnFXWWKwtwYjHhhkcczlWjASAWMZplAsgoT4Swz6U6BN3rLb1EAhbVmEUzVOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:18:02.892966Z","bundle_sha256":"3fa1ca494c5a5718c3cdad67a1de5ccc1d0074dfe904f09db6c10d11db8c5c22"}}