{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AICTRR3TDBSHOXIKRT3BWR5CRQ","short_pith_number":"pith:AICTRR3T","schema_version":"1.0","canonical_sha256":"020538c7731864775d0a8cf61b47a28c0b382a3b38f5c274d9329a8c54fee65d","source":{"kind":"arxiv","id":"2509.10844","version":1},"attestation_state":"computed","paper":{"title":"GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yixuan Tang, Yi Yang","submitted_at":"2025-09-13T15:03:37Z","abstract_excerpt":"Domain-specific embedding models have shown promise for applications that require specialized semantic understanding, such as coding agents and financial retrieval systems, often achieving higher performance gains than general models. However, state-of-the-art embedding models are typically based on LLMs, which contain billions of parameters, making deployment challenging in resource-constrained environments. Model compression through pruning offers a promising solution, but existing pruning methods treat all parameters uniformly, failing to distinguish between general semantic representations"},"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":"2509.10844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-13T15:03:37Z","cross_cats_sorted":[],"title_canon_sha256":"ffa0937933a99c21952f29478e47761047d99591153faed3e78005535736ff38","abstract_canon_sha256":"a640500effe76d3e3c1de13b6423c759c44c853d1ce63a425d5d307414835b53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:29.047654Z","signature_b64":"SCOr8rkFqubbW6HZwhPvRzI2ItcKEM7xDC1Pajv1TPKz9edrJyLiRNInUHdm9guZZ4HlVCtaAY2i+EYHSQj2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"020538c7731864775d0a8cf61b47a28c0b382a3b38f5c274d9329a8c54fee65d","last_reissued_at":"2026-07-05T12:11:29.047125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:29.047125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yixuan Tang, Yi Yang","submitted_at":"2025-09-13T15:03:37Z","abstract_excerpt":"Domain-specific embedding models have shown promise for applications that require specialized semantic understanding, such as coding agents and financial retrieval systems, often achieving higher performance gains than general models. However, state-of-the-art embedding models are typically based on LLMs, which contain billions of parameters, making deployment challenging in resource-constrained environments. Model compression through pruning offers a promising solution, but existing pruning methods treat all parameters uniformly, failing to distinguish between general semantic representations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10844","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/2509.10844/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":"2509.10844","created_at":"2026-07-05T12:11:29.047179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10844v1","created_at":"2026-07-05T12:11:29.047179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10844","created_at":"2026-07-05T12:11:29.047179+00:00"},{"alias_kind":"pith_short_12","alias_value":"AICTRR3TDBSH","created_at":"2026-07-05T12:11:29.047179+00:00"},{"alias_kind":"pith_short_16","alias_value":"AICTRR3TDBSHOXIK","created_at":"2026-07-05T12:11:29.047179+00:00"},{"alias_kind":"pith_short_8","alias_value":"AICTRR3T","created_at":"2026-07-05T12:11:29.047179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24774","citing_title":"Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ","json":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ.json","graph_json":"https://pith.science/api/pith-number/AICTRR3TDBSHOXIKRT3BWR5CRQ/graph.json","events_json":"https://pith.science/api/pith-number/AICTRR3TDBSHOXIKRT3BWR5CRQ/events.json","paper":"https://pith.science/paper/AICTRR3T"},"agent_actions":{"view_html":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ","download_json":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ.json","view_paper":"https://pith.science/paper/AICTRR3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10844&json=true","fetch_graph":"https://pith.science/api/pith-number/AICTRR3TDBSHOXIKRT3BWR5CRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AICTRR3TDBSHOXIKRT3BWR5CRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ/action/storage_attestation","attest_author":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ/action/author_attestation","sign_citation":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ/action/citation_signature","submit_replication":"https://pith.science/pith/AICTRR3TDBSHOXIKRT3BWR5CRQ/action/replication_record"}},"created_at":"2026-07-05T12:11:29.047179+00:00","updated_at":"2026-07-05T12:11:29.047179+00:00"}