{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WGBE4C7IMTUDCLO5LX5VBOENPI","short_pith_number":"pith:WGBE4C7I","canonical_record":{"source":{"id":"2501.15296","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T18:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"6876bb8856fa49c1f3abc74315f347b39d846fa10f617481ba61f7641b26fafc","abstract_canon_sha256":"a2716aec2959f89e90505f526dfbd63e404f408971a31371b904fd588272e5cb"},"schema_version":"1.0"},"canonical_sha256":"b1824e0be864e8312ddd5dfb50b88d7a1e0915e806f6a9baa58ae89cb6c30fe4","source":{"kind":"arxiv","id":"2501.15296","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15296","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15296v3","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15296","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"WGBE4C7IMTUD","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"WGBE4C7IMTUDCLO5","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"WGBE4C7I","created_at":"2026-07-05T10:21:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WGBE4C7IMTUDCLO5LX5VBOENPI","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15296","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T18:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"6876bb8856fa49c1f3abc74315f347b39d846fa10f617481ba61f7641b26fafc","abstract_canon_sha256":"a2716aec2959f89e90505f526dfbd63e404f408971a31371b904fd588272e5cb"},"schema_version":"1.0"},"canonical_sha256":"b1824e0be864e8312ddd5dfb50b88d7a1e0915e806f6a9baa58ae89cb6c30fe4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:28.402661Z","signature_b64":"PFWMuJg1ArftvSfqTlG+VBCj/YVrRhM0vxdeGXpz/TlC7lYV5Y0+V+AThSEBqIGc/xaFIilXk4ZYNPey51FvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1824e0be864e8312ddd5dfb50b88d7a1e0915e806f6a9baa58ae89cb6c30fe4","last_reissued_at":"2026-07-05T10:21:28.402133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:28.402133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15296","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9duGDOAyo+pWvursv8ERYyK3PpW1OUSxoMtRldDkIRCqAQfv2WtZuxFfWwDAfxuLe/w9Qtr3KmEb5KaBEQpHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:39:56.141131Z"},"content_sha256":"0569242d1509a7c3dec5764052649ac985be7cae6e718702798342cef01ee9d2","schema_version":"1.0","event_id":"sha256:0569242d1509a7c3dec5764052649ac985be7cae6e718702798342cef01ee9d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WGBE4C7IMTUDCLO5LX5VBOENPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty","submitted_at":"2025-01-25T18:26:39Z","abstract_excerpt":"The ever-increasing size of large language models (LLMs) presents significant challenges for deployment due to their heavy computational and memory requirements. Current model pruning techniques attempt to alleviate these issues by relying heavily on external calibration datasets to determine which parameters to prune or compress, thus limiting their flexibility and scalability across different compression ratios. Moreover, these methods often cause severe performance degradation, particularly in downstream tasks, when subjected to higher compression rates. In this paper, we propose PruneNet, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15296","kind":"arxiv","version":3},"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/2501.15296/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":"2026-07-05T10:21:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8caa/CngClF24AeBOs6W2Ls/hTIE6kh00kbT/0NfXCmnOlvTS8Z1fMk18JhViTPjq632dFxwm3X1dJ7Y36Y2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:39:56.142024Z"},"content_sha256":"75877cdf67b4ae88ce1c10f3af17c107298555783988f0c7d9360e113bc37f51","schema_version":"1.0","event_id":"sha256:75877cdf67b4ae88ce1c10f3af17c107298555783988f0c7d9360e113bc37f51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WGBE4C7IMTUDCLO5LX5VBOENPI/bundle.json","state_url":"https://pith.science/pith/WGBE4C7IMTUDCLO5LX5VBOENPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WGBE4C7IMTUDCLO5LX5VBOENPI/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":"2026-08-08T18:39:56Z","links":{"resolver":"https://pith.science/pith/WGBE4C7IMTUDCLO5LX5VBOENPI","bundle":"https://pith.science/pith/WGBE4C7IMTUDCLO5LX5VBOENPI/bundle.json","state":"https://pith.science/pith/WGBE4C7IMTUDCLO5LX5VBOENPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WGBE4C7IMTUDCLO5LX5VBOENPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WGBE4C7IMTUDCLO5LX5VBOENPI","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":"a2716aec2959f89e90505f526dfbd63e404f408971a31371b904fd588272e5cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T18:26:39Z","title_canon_sha256":"6876bb8856fa49c1f3abc74315f347b39d846fa10f617481ba61f7641b26fafc"},"schema_version":"1.0","source":{"id":"2501.15296","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15296","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15296v3","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15296","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"WGBE4C7IMTUD","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"WGBE4C7IMTUDCLO5","created_at":"2026-07-05T10:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"WGBE4C7I","created_at":"2026-07-05T10:21:28Z"}],"graph_snapshots":[{"event_id":"sha256:75877cdf67b4ae88ce1c10f3af17c107298555783988f0c7d9360e113bc37f51","target":"graph","created_at":"2026-07-05T10:21:28Z","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/2501.15296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ever-increasing size of large language models (LLMs) presents significant challenges for deployment due to their heavy computational and memory requirements. Current model pruning techniques attempt to alleviate these issues by relying heavily on external calibration datasets to determine which parameters to prune or compress, thus limiting their flexibility and scalability across different compression ratios. Moreover, these methods often cause severe performance degradation, particularly in downstream tasks, when subjected to higher compression rates. In this paper, we propose PruneNet, ","authors_text":"Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T18:26:39Z","title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15296","kind":"arxiv","version":3},"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":"sha256:0569242d1509a7c3dec5764052649ac985be7cae6e718702798342cef01ee9d2","target":"record","created_at":"2026-07-05T10:21:28Z","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":"a2716aec2959f89e90505f526dfbd63e404f408971a31371b904fd588272e5cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T18:26:39Z","title_canon_sha256":"6876bb8856fa49c1f3abc74315f347b39d846fa10f617481ba61f7641b26fafc"},"schema_version":"1.0","source":{"id":"2501.15296","kind":"arxiv","version":3}},"canonical_sha256":"b1824e0be864e8312ddd5dfb50b88d7a1e0915e806f6a9baa58ae89cb6c30fe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1824e0be864e8312ddd5dfb50b88d7a1e0915e806f6a9baa58ae89cb6c30fe4","first_computed_at":"2026-07-05T10:21:28.402133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:28.402133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PFWMuJg1ArftvSfqTlG+VBCj/YVrRhM0vxdeGXpz/TlC7lYV5Y0+V+AThSEBqIGc/xaFIilXk4ZYNPey51FvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:28.402661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15296","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0569242d1509a7c3dec5764052649ac985be7cae6e718702798342cef01ee9d2","sha256:75877cdf67b4ae88ce1c10f3af17c107298555783988f0c7d9360e113bc37f51"],"state_sha256":"7815917dffc05970ef5e5904c4f7c7b8ef5e87be3eb748dc960a09e41917133b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"87UR0b3tdaMD4xPgEEYRAdKuJnoP/4wGOreAewaHsB/0c9bPsQPo3mrFx1nopQXQUi4g6YIVCxdSZYsNsBSwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:39:56.148174Z","bundle_sha256":"1007503cfe6fdd7c08d36493d9c148a53f48aeaecd74825d554b3d9dd7cdb84b"}}