{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4IX7NE57OXBPGE4ECCWJ5XHGDV","short_pith_number":"pith:4IX7NE57","canonical_record":{"source":{"id":"2403.16020","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T05:50:00Z","cross_cats_sorted":[],"title_canon_sha256":"cb4e1b676068047fd80288d8e8d2cb4eeae92456a510b0e16d4cb20e3672f9ee","abstract_canon_sha256":"581c5c7c7db8ac201f1dd41515b634564d2492cbf9383704c48fe1df82302b33"},"schema_version":"1.0"},"canonical_sha256":"e22ff693bf75c2f3138410ac9edce61d51ca2c405d826ad18a3f7cdbc4b2c5f5","source":{"kind":"arxiv","id":"2403.16020","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16020","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16020v2","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16020","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_12","alias_value":"4IX7NE57OXBP","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_16","alias_value":"4IX7NE57OXBPGE4E","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_8","alias_value":"4IX7NE57","created_at":"2026-07-05T08:39:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4IX7NE57OXBPGE4ECCWJ5XHGDV","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16020","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T05:50:00Z","cross_cats_sorted":[],"title_canon_sha256":"cb4e1b676068047fd80288d8e8d2cb4eeae92456a510b0e16d4cb20e3672f9ee","abstract_canon_sha256":"581c5c7c7db8ac201f1dd41515b634564d2492cbf9383704c48fe1df82302b33"},"schema_version":"1.0"},"canonical_sha256":"e22ff693bf75c2f3138410ac9edce61d51ca2c405d826ad18a3f7cdbc4b2c5f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:32.652005Z","signature_b64":"laoB67UX6jgT7zvXLdESYUgAKlYlQKr/uZ/5n7igs7N9iF3ZW51SSvGQRrkdpOXxVcMkJyQ1s8I7MzuM9F8PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e22ff693bf75c2f3138410ac9edce61d51ca2c405d826ad18a3f7cdbc4b2c5f5","last_reissued_at":"2026-07-05T08:39:32.651479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:32.651479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16020","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:39:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tOuIPW8s65yKyWykWLGujEZH59Qn0cjXc9avHyamjdLQNdhcO/Xz/JAP8D71tGMgmwItBo83Tuu0g0T4DTJ/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:02:57.494391Z"},"content_sha256":"683047ba614ad319fd786595f8a75265c3165bc1aaf6db7cafc30ed2699e175e","schema_version":"1.0","event_id":"sha256:683047ba614ad319fd786595f8a75265c3165bc1aaf6db7cafc30ed2699e175e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4IX7NE57OXBPGE4ECCWJ5XHGDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Burhaneddin Yaman, Chun-Hao Liu, Diana Marculescu, Tanvir Mahmud","submitted_at":"2024-03-24T05:50:00Z","abstract_excerpt":"As deep neural networks evolve from convolutional neural networks (ConvNets) to advanced vision transformers (ViTs), there is an increased need to eliminate redundant data for faster processing without compromising accuracy. Previous methods are often architecture-specific or necessitate re-training, restricting their applicability with frequent model updates. To solve this, we first introduce a novel property of lightweight ConvNets: their ability to identify key discriminative patch regions in images, irrespective of model's final accuracy or size. We demonstrate that fully-connected layers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16020","kind":"arxiv","version":2},"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/2403.16020/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":"2026-07-05T08:39:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/03MdGEt+QxTTdp4Ec6lNogY+nbTi9/xli2CdbEnuT8ORzCPPmZ3C6vjIYTHosmJ0SstKSjiZp6cUO7TBoPgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:02:57.495607Z"},"content_sha256":"2a458f66c24d7b3cc3f7ccf3612d67701eb3b3dee8cfbe61de52d92b5d3b4dd1","schema_version":"1.0","event_id":"sha256:2a458f66c24d7b3cc3f7ccf3612d67701eb3b3dee8cfbe61de52d92b5d3b4dd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV/bundle.json","state_url":"https://pith.science/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV/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":"2026-07-05T15:02:57Z","links":{"resolver":"https://pith.science/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV","bundle":"https://pith.science/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV/bundle.json","state":"https://pith.science/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IX7NE57OXBPGE4ECCWJ5XHGDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4IX7NE57OXBPGE4ECCWJ5XHGDV","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":"581c5c7c7db8ac201f1dd41515b634564d2492cbf9383704c48fe1df82302b33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T05:50:00Z","title_canon_sha256":"cb4e1b676068047fd80288d8e8d2cb4eeae92456a510b0e16d4cb20e3672f9ee"},"schema_version":"1.0","source":{"id":"2403.16020","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16020","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16020v2","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16020","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_12","alias_value":"4IX7NE57OXBP","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_16","alias_value":"4IX7NE57OXBPGE4E","created_at":"2026-07-05T08:39:32Z"},{"alias_kind":"pith_short_8","alias_value":"4IX7NE57","created_at":"2026-07-05T08:39:32Z"}],"graph_snapshots":[{"event_id":"sha256:2a458f66c24d7b3cc3f7ccf3612d67701eb3b3dee8cfbe61de52d92b5d3b4dd1","target":"graph","created_at":"2026-07-05T08:39:32Z","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/2403.16020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As deep neural networks evolve from convolutional neural networks (ConvNets) to advanced vision transformers (ViTs), there is an increased need to eliminate redundant data for faster processing without compromising accuracy. Previous methods are often architecture-specific or necessitate re-training, restricting their applicability with frequent model updates. To solve this, we first introduce a novel property of lightweight ConvNets: their ability to identify key discriminative patch regions in images, irrespective of model's final accuracy or size. We demonstrate that fully-connected layers ","authors_text":"Burhaneddin Yaman, Chun-Hao Liu, Diana Marculescu, Tanvir Mahmud","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T05:50:00Z","title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16020","kind":"arxiv","version":2},"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":"sha256:683047ba614ad319fd786595f8a75265c3165bc1aaf6db7cafc30ed2699e175e","target":"record","created_at":"2026-07-05T08:39:32Z","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":"581c5c7c7db8ac201f1dd41515b634564d2492cbf9383704c48fe1df82302b33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T05:50:00Z","title_canon_sha256":"cb4e1b676068047fd80288d8e8d2cb4eeae92456a510b0e16d4cb20e3672f9ee"},"schema_version":"1.0","source":{"id":"2403.16020","kind":"arxiv","version":2}},"canonical_sha256":"e22ff693bf75c2f3138410ac9edce61d51ca2c405d826ad18a3f7cdbc4b2c5f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e22ff693bf75c2f3138410ac9edce61d51ca2c405d826ad18a3f7cdbc4b2c5f5","first_computed_at":"2026-07-05T08:39:32.651479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:32.651479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"laoB67UX6jgT7zvXLdESYUgAKlYlQKr/uZ/5n7igs7N9iF3ZW51SSvGQRrkdpOXxVcMkJyQ1s8I7MzuM9F8PDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:32.652005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16020","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:683047ba614ad319fd786595f8a75265c3165bc1aaf6db7cafc30ed2699e175e","sha256:2a458f66c24d7b3cc3f7ccf3612d67701eb3b3dee8cfbe61de52d92b5d3b4dd1"],"state_sha256":"900b3a8546f94f83869f9f10b5c8aaab99d57d0a7c7998dd767e016823ee46b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9xP32oXcIKGPC6b9LfTp9SVvXSJI46drMCd58JEebsAJG9dB1SFvvCLOiOnC1Kx+ZbdGR9yMxVI7/jwCD3YCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:02:57.500139Z","bundle_sha256":"4a76a9827ca84f64956a0d9066d3e01244a942ccf17858de47d57c4dd7390668"}}