{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:U24DAAFGWPOF6YBMOMOMYKSSWA","short_pith_number":"pith:U24DAAFG","canonical_record":{"source":{"id":"2207.00112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T21:57:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4d8d652d4fcfa64221d23c0b1b36ab7539754033eceb67d09add5c0ae5a73e7d","abstract_canon_sha256":"7530c6873eb496345fbe02fb3d53b91651d4ab01b7a2ee154b141757b723133d"},"schema_version":"1.0"},"canonical_sha256":"a6b83000a6b3dc5f602c731ccc2a52b03f8008d61bc7a03f894cf90f15a180c5","source":{"kind":"arxiv","id":"2207.00112","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00112","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00112v1","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00112","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"U24DAAFGWPOF","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"U24DAAFGWPOF6YBM","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"U24DAAFG","created_at":"2026-07-05T04:36:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:U24DAAFGWPOF6YBMOMOMYKSSWA","target":"record","payload":{"canonical_record":{"source":{"id":"2207.00112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T21:57:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4d8d652d4fcfa64221d23c0b1b36ab7539754033eceb67d09add5c0ae5a73e7d","abstract_canon_sha256":"7530c6873eb496345fbe02fb3d53b91651d4ab01b7a2ee154b141757b723133d"},"schema_version":"1.0"},"canonical_sha256":"a6b83000a6b3dc5f602c731ccc2a52b03f8008d61bc7a03f894cf90f15a180c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:39.191131Z","signature_b64":"9kiafoQNoIkh/l/nxypfahDpnHOjNQRQ6pYiT+aGj77oFC39TsJvE4kRGOghnNqidQKvvWN36VslE8PhLzHIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6b83000a6b3dc5f602c731ccc2a52b03f8008d61bc7a03f894cf90f15a180c5","last_reissued_at":"2026-07-05T04:36:39.190676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:39.190676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.00112","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":"2026-07-05T04:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQVRonzP81cHiPsTSK0p8UcNRKTivsv6leGZKaoe38Vmhgtj2aRjJnDjW2xy5e9UHb47w9Ct8TImdckhMDEjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:11:32.512600Z"},"content_sha256":"f6192afc82f6ff4274d6f27910c5c3577829a13e0ec21223eede0c3746b776fb","schema_version":"1.0","event_id":"sha256:f6192afc82f6ff4274d6f27910c5c3577829a13e0ec21223eede0c3746b776fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:U24DAAFGWPOF6YBMOMOMYKSSWA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language model compression with weighted low-rank factorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongxia Jin, Qian Lou, Sungen Chang, Ting Hua, Yen-Chang Hsu, Yilin Shen","submitted_at":"2022-06-30T21:57:07Z","abstract_excerpt":"Factorizing a large matrix into small matrices is a popular strategy for model compression. Singular value decomposition (SVD) plays a vital role in this compression strategy, approximating a learned matrix with fewer parameters. However, SVD minimizes the squared error toward reconstructing the original matrix without gauging the importance of the parameters, potentially giving a larger reconstruction error for those who affect the task accuracy more. In other words, the optimization objective of SVD is not aligned with the trained model's task accuracy. We analyze this previously unexplored "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00112","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/2207.00112/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":"2026-07-05T04:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DOz5jSA6gMW4n477njOyWS/RiiP5AnsCWEbQV46/wXY2F3UJrKDdvg+ErTi72FN3loCT/vEdK11m1p4P6fuaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:11:32.513532Z"},"content_sha256":"45664506747fc527d0185f645d35b026a7a8d133fd0ac5d82b978418e1a835f0","schema_version":"1.0","event_id":"sha256:45664506747fc527d0185f645d35b026a7a8d133fd0ac5d82b978418e1a835f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U24DAAFGWPOF6YBMOMOMYKSSWA/bundle.json","state_url":"https://pith.science/pith/U24DAAFGWPOF6YBMOMOMYKSSWA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U24DAAFGWPOF6YBMOMOMYKSSWA/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":"2026-08-07T00:11:32Z","links":{"resolver":"https://pith.science/pith/U24DAAFGWPOF6YBMOMOMYKSSWA","bundle":"https://pith.science/pith/U24DAAFGWPOF6YBMOMOMYKSSWA/bundle.json","state":"https://pith.science/pith/U24DAAFGWPOF6YBMOMOMYKSSWA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U24DAAFGWPOF6YBMOMOMYKSSWA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:U24DAAFGWPOF6YBMOMOMYKSSWA","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":"7530c6873eb496345fbe02fb3d53b91651d4ab01b7a2ee154b141757b723133d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T21:57:07Z","title_canon_sha256":"4d8d652d4fcfa64221d23c0b1b36ab7539754033eceb67d09add5c0ae5a73e7d"},"schema_version":"1.0","source":{"id":"2207.00112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00112","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00112v1","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00112","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"U24DAAFGWPOF","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"U24DAAFGWPOF6YBM","created_at":"2026-07-05T04:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"U24DAAFG","created_at":"2026-07-05T04:36:39Z"}],"graph_snapshots":[{"event_id":"sha256:45664506747fc527d0185f645d35b026a7a8d133fd0ac5d82b978418e1a835f0","target":"graph","created_at":"2026-07-05T04:36:39Z","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/2207.00112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Factorizing a large matrix into small matrices is a popular strategy for model compression. Singular value decomposition (SVD) plays a vital role in this compression strategy, approximating a learned matrix with fewer parameters. However, SVD minimizes the squared error toward reconstructing the original matrix without gauging the importance of the parameters, potentially giving a larger reconstruction error for those who affect the task accuracy more. In other words, the optimization objective of SVD is not aligned with the trained model's task accuracy. We analyze this previously unexplored ","authors_text":"Hongxia Jin, Qian Lou, Sungen Chang, Ting Hua, Yen-Chang Hsu, Yilin Shen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T21:57:07Z","title":"Language model compression with weighted low-rank factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00112","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:f6192afc82f6ff4274d6f27910c5c3577829a13e0ec21223eede0c3746b776fb","target":"record","created_at":"2026-07-05T04:36:39Z","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":"7530c6873eb496345fbe02fb3d53b91651d4ab01b7a2ee154b141757b723133d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T21:57:07Z","title_canon_sha256":"4d8d652d4fcfa64221d23c0b1b36ab7539754033eceb67d09add5c0ae5a73e7d"},"schema_version":"1.0","source":{"id":"2207.00112","kind":"arxiv","version":1}},"canonical_sha256":"a6b83000a6b3dc5f602c731ccc2a52b03f8008d61bc7a03f894cf90f15a180c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6b83000a6b3dc5f602c731ccc2a52b03f8008d61bc7a03f894cf90f15a180c5","first_computed_at":"2026-07-05T04:36:39.190676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:39.190676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9kiafoQNoIkh/l/nxypfahDpnHOjNQRQ6pYiT+aGj77oFC39TsJvE4kRGOghnNqidQKvvWN36VslE8PhLzHIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:39.191131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6192afc82f6ff4274d6f27910c5c3577829a13e0ec21223eede0c3746b776fb","sha256:45664506747fc527d0185f645d35b026a7a8d133fd0ac5d82b978418e1a835f0"],"state_sha256":"1757c8dbac1400c891cd6e78c61a95a7fe7e963c7ea7fb786e72389bf69014fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lg93DocmW01qi7ty++PxKmhbPj3z0A0Dj+T0sdz+mudTwVNjQllxmo81DSegsRFphRpBoKLXSH41gkVEmNI/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:11:32.703315Z","bundle_sha256":"24a57eac6a75ef5df4d630a464800666388d1a021c8c29d1fdd3e1a932acc9fe"}}