{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QPDKVUN3S2FU33F7C2TO42JM7S","short_pith_number":"pith:QPDKVUN3","canonical_record":{"source":{"id":"2303.08595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-14T02:47:57Z","cross_cats_sorted":[],"title_canon_sha256":"7d5c5fbd4b9a7820a9465987d8e262996ff8ff8fb5519f6e9ca5e0202b0e2039","abstract_canon_sha256":"eef9b291503ca4ad4b6cd3101c7ec00d31fbfa860324cc055dbc55296802f899"},"schema_version":"1.0"},"canonical_sha256":"83c6aad1bb968b4decbf16a6ee692cfc963ce399bead6846a17b7879ef088425","source":{"kind":"arxiv","id":"2303.08595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08595","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08595v1","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08595","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"QPDKVUN3S2FU","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"QPDKVUN3S2FU33F7","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"QPDKVUN3","created_at":"2026-07-05T05:51:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QPDKVUN3S2FU33F7C2TO42JM7S","target":"record","payload":{"canonical_record":{"source":{"id":"2303.08595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-14T02:47:57Z","cross_cats_sorted":[],"title_canon_sha256":"7d5c5fbd4b9a7820a9465987d8e262996ff8ff8fb5519f6e9ca5e0202b0e2039","abstract_canon_sha256":"eef9b291503ca4ad4b6cd3101c7ec00d31fbfa860324cc055dbc55296802f899"},"schema_version":"1.0"},"canonical_sha256":"83c6aad1bb968b4decbf16a6ee692cfc963ce399bead6846a17b7879ef088425","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:35.002275Z","signature_b64":"Jigyq+DqE2n/rk9Pg4hRnYPfjfQPqKgU1wd9Tl8lVv0ezQHa1ESSNlgpbt0gnitYXL5/hVvJj4v+Liqyxf07BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83c6aad1bb968b4decbf16a6ee692cfc963ce399bead6846a17b7879ef088425","last_reissued_at":"2026-07-05T05:51:35.001925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:35.001925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.08595","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":"2026-07-05T05:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9Sf6KVA3Se9BDEwM0OWTT4stGANuav70z6x6bY1ssp0HPKNNXJBmjmwpSPaOIzmvvcrUwzgpFXHlLc3GntdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:50:41.099871Z"},"content_sha256":"c0e7fe01c17deedbffdd81367c9d3ffef0bc74ce53df618f6dc8e99166a3afb6","schema_version":"1.0","event_id":"sha256:c0e7fe01c17deedbffdd81367c9d3ffef0bc74ce53df618f6dc8e99166a3afb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QPDKVUN3S2FU33F7C2TO42JM7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Animesh Jain, Kaiqi Zhao, Ming Zhao","submitted_at":"2023-03-14T02:47:57Z","abstract_excerpt":"Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware; and they often require users to manually explore and tune the pruning process, which is time-consuming and often leads to sub-optimal results. To address these limitations, this paper presents Automatic Attention Pruning (AAP), an adaptive, attention-based, structured pruning approach to automatically generate small, accurat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08595","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/2303.08595/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":"2026-07-05T05:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fi+z1N3wyPjnVS3uU17sZdWy4REUJ4vXVjznYQ9ooNoniAEAAHCOYlvmvHYn3YcYc3oKoWMhYE2i+JlCoMweCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:50:41.100420Z"},"content_sha256":"825a6d717e63874b3bd1ac5af29f6986cb720985103dc0e13a704e0746667f08","schema_version":"1.0","event_id":"sha256:825a6d717e63874b3bd1ac5af29f6986cb720985103dc0e13a704e0746667f08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPDKVUN3S2FU33F7C2TO42JM7S/bundle.json","state_url":"https://pith.science/pith/QPDKVUN3S2FU33F7C2TO42JM7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPDKVUN3S2FU33F7C2TO42JM7S/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":"2026-08-09T10:50:41Z","links":{"resolver":"https://pith.science/pith/QPDKVUN3S2FU33F7C2TO42JM7S","bundle":"https://pith.science/pith/QPDKVUN3S2FU33F7C2TO42JM7S/bundle.json","state":"https://pith.science/pith/QPDKVUN3S2FU33F7C2TO42JM7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPDKVUN3S2FU33F7C2TO42JM7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QPDKVUN3S2FU33F7C2TO42JM7S","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":"eef9b291503ca4ad4b6cd3101c7ec00d31fbfa860324cc055dbc55296802f899","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-14T02:47:57Z","title_canon_sha256":"7d5c5fbd4b9a7820a9465987d8e262996ff8ff8fb5519f6e9ca5e0202b0e2039"},"schema_version":"1.0","source":{"id":"2303.08595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08595","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08595v1","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08595","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"QPDKVUN3S2FU","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"QPDKVUN3S2FU33F7","created_at":"2026-07-05T05:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"QPDKVUN3","created_at":"2026-07-05T05:51:35Z"}],"graph_snapshots":[{"event_id":"sha256:825a6d717e63874b3bd1ac5af29f6986cb720985103dc0e13a704e0746667f08","target":"graph","created_at":"2026-07-05T05:51:35Z","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/2303.08595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot efficiently run on commodity hardware; and they often require users to manually explore and tune the pruning process, which is time-consuming and often leads to sub-optimal results. To address these limitations, this paper presents Automatic Attention Pruning (AAP), an adaptive, attention-based, structured pruning approach to automatically generate small, accurat","authors_text":"Animesh Jain, Kaiqi Zhao, Ming Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-14T02:47:57Z","title":"Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08595","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:c0e7fe01c17deedbffdd81367c9d3ffef0bc74ce53df618f6dc8e99166a3afb6","target":"record","created_at":"2026-07-05T05:51:35Z","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":"eef9b291503ca4ad4b6cd3101c7ec00d31fbfa860324cc055dbc55296802f899","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-14T02:47:57Z","title_canon_sha256":"7d5c5fbd4b9a7820a9465987d8e262996ff8ff8fb5519f6e9ca5e0202b0e2039"},"schema_version":"1.0","source":{"id":"2303.08595","kind":"arxiv","version":1}},"canonical_sha256":"83c6aad1bb968b4decbf16a6ee692cfc963ce399bead6846a17b7879ef088425","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83c6aad1bb968b4decbf16a6ee692cfc963ce399bead6846a17b7879ef088425","first_computed_at":"2026-07-05T05:51:35.001925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:35.001925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jigyq+DqE2n/rk9Pg4hRnYPfjfQPqKgU1wd9Tl8lVv0ezQHa1ESSNlgpbt0gnitYXL5/hVvJj4v+Liqyxf07BA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:35.002275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.08595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0e7fe01c17deedbffdd81367c9d3ffef0bc74ce53df618f6dc8e99166a3afb6","sha256:825a6d717e63874b3bd1ac5af29f6986cb720985103dc0e13a704e0746667f08"],"state_sha256":"a74fb26b23936f37198f0fc6a224edc9ed37e309422f06926e280c8c3feaf1a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5h4zdEIMIe5mVLmbsSMWcWq2BhJ2mgUsl693diq21Bnukil5GkgbfIsD+LPnh2wIzeXhURxtU1H5YavCBrMdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:50:41.106527Z","bundle_sha256":"95336ac6dd49b9c2f4faeb491e3c493451a851ab7bc1e641099029d3ae0b9c65"}}