{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3IB75ARZPKAW3RSXA7RPK3TTMO","short_pith_number":"pith:3IB75ARZ","canonical_record":{"source":{"id":"2508.12891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T12:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"00f1c1dea6e34a75dff5ef17061ea8663c1be13bceafbaeb722cb1a1278068a1","abstract_canon_sha256":"214c9f42b2876b4d2852d57da2b4dd3ff9ed169fc545f8c5a90b4e6b4f84e49d"},"schema_version":"1.0"},"canonical_sha256":"da03fe82397a816dc65707e2f56e7363a885210a8d154a8b7671909833027902","source":{"kind":"arxiv","id":"2508.12891","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12891","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12891v1","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12891","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"3IB75ARZPKAW","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"3IB75ARZPKAW3RSX","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"3IB75ARZ","created_at":"2026-07-05T11:55:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3IB75ARZPKAW3RSXA7RPK3TTMO","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T12:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"00f1c1dea6e34a75dff5ef17061ea8663c1be13bceafbaeb722cb1a1278068a1","abstract_canon_sha256":"214c9f42b2876b4d2852d57da2b4dd3ff9ed169fc545f8c5a90b4e6b4f84e49d"},"schema_version":"1.0"},"canonical_sha256":"da03fe82397a816dc65707e2f56e7363a885210a8d154a8b7671909833027902","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:28.920741Z","signature_b64":"kQ38Pvao2gE2ssMLY29/3A2AvhRHnw2qPMN0DHxyXeaqralTw8nwNt+A30FvIo7eyvMAQW8Y7avZfGKMnVjqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da03fe82397a816dc65707e2f56e7363a885210a8d154a8b7671909833027902","last_reissued_at":"2026-07-05T11:55:28.920242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:28.920242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12891","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":"2026-07-05T11:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"47G6jsLOoyPWrDUkr/uTefCOt2BwGcOikSSgv+oarkw8HMf6bqmzZYIkhSAtsN4jKPDQ+iOV7ucTSrGLFK2oAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:46:49.638545Z"},"content_sha256":"cc016afe08508011ab3dc8d41a131330aec3498a7a044388c829588c1cde893b","schema_version":"1.0","event_id":"sha256:cc016afe08508011ab3dc8d41a131330aec3498a7a044388c829588c1cde893b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3IB75ARZPKAW3RSXA7RPK3TTMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ONG: One-Shot NMF-based Gradient Masking for Efficient Model Sparsification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sankar Behera, Yamuna Prasad","submitted_at":"2025-08-18T12:46:05Z","abstract_excerpt":"Deep Neural Networks (DNNs) have achieved remarkable success but their large size poses deployment challenges. While various pruning techniques exist, many involve complex iterative processes, specialized criteria, or struggle to maintain sparsity effectively during training. We introduce ONG (One-shot NMF-based Gradient Masking), a novel sparsification strategy that identifies salient weight structures using Non-negative Matrix Factorization (NMF) for one-shot pruning at the outset of training. Subsequently, ONG employs a precise gradient masking mechanism to ensure that only unpruned weights"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12891","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/2508.12891/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":"2026-07-05T11:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"caK8iCBz3kPBqdfxcWaElnYVyZ3Ss/TuEYHx2EMe0v/DKVQCjw9edcub1tiaPZv5JIYdTXTNzJ3U+bNUgCopDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:46:49.639447Z"},"content_sha256":"f0dc34e2fb8a8fc2a2ee955e74823bd41539b28801ecdd8b3882f47b0d17c8b5","schema_version":"1.0","event_id":"sha256:f0dc34e2fb8a8fc2a2ee955e74823bd41539b28801ecdd8b3882f47b0d17c8b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IB75ARZPKAW3RSXA7RPK3TTMO/bundle.json","state_url":"https://pith.science/pith/3IB75ARZPKAW3RSXA7RPK3TTMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IB75ARZPKAW3RSXA7RPK3TTMO/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":"2026-08-17T18:46:49Z","links":{"resolver":"https://pith.science/pith/3IB75ARZPKAW3RSXA7RPK3TTMO","bundle":"https://pith.science/pith/3IB75ARZPKAW3RSXA7RPK3TTMO/bundle.json","state":"https://pith.science/pith/3IB75ARZPKAW3RSXA7RPK3TTMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IB75ARZPKAW3RSXA7RPK3TTMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3IB75ARZPKAW3RSXA7RPK3TTMO","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":"214c9f42b2876b4d2852d57da2b4dd3ff9ed169fc545f8c5a90b4e6b4f84e49d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T12:46:05Z","title_canon_sha256":"00f1c1dea6e34a75dff5ef17061ea8663c1be13bceafbaeb722cb1a1278068a1"},"schema_version":"1.0","source":{"id":"2508.12891","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12891","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12891v1","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12891","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"3IB75ARZPKAW","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"3IB75ARZPKAW3RSX","created_at":"2026-07-05T11:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"3IB75ARZ","created_at":"2026-07-05T11:55:28Z"}],"graph_snapshots":[{"event_id":"sha256:f0dc34e2fb8a8fc2a2ee955e74823bd41539b28801ecdd8b3882f47b0d17c8b5","target":"graph","created_at":"2026-07-05T11:55:28Z","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/2508.12891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Neural Networks (DNNs) have achieved remarkable success but their large size poses deployment challenges. While various pruning techniques exist, many involve complex iterative processes, specialized criteria, or struggle to maintain sparsity effectively during training. We introduce ONG (One-shot NMF-based Gradient Masking), a novel sparsification strategy that identifies salient weight structures using Non-negative Matrix Factorization (NMF) for one-shot pruning at the outset of training. Subsequently, ONG employs a precise gradient masking mechanism to ensure that only unpruned weights","authors_text":"Sankar Behera, Yamuna Prasad","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T12:46:05Z","title":"ONG: One-Shot NMF-based Gradient Masking for Efficient Model Sparsification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12891","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:cc016afe08508011ab3dc8d41a131330aec3498a7a044388c829588c1cde893b","target":"record","created_at":"2026-07-05T11:55:28Z","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":"214c9f42b2876b4d2852d57da2b4dd3ff9ed169fc545f8c5a90b4e6b4f84e49d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T12:46:05Z","title_canon_sha256":"00f1c1dea6e34a75dff5ef17061ea8663c1be13bceafbaeb722cb1a1278068a1"},"schema_version":"1.0","source":{"id":"2508.12891","kind":"arxiv","version":1}},"canonical_sha256":"da03fe82397a816dc65707e2f56e7363a885210a8d154a8b7671909833027902","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da03fe82397a816dc65707e2f56e7363a885210a8d154a8b7671909833027902","first_computed_at":"2026-07-05T11:55:28.920242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:28.920242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kQ38Pvao2gE2ssMLY29/3A2AvhRHnw2qPMN0DHxyXeaqralTw8nwNt+A30FvIo7eyvMAQW8Y7avZfGKMnVjqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:28.920741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12891","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc016afe08508011ab3dc8d41a131330aec3498a7a044388c829588c1cde893b","sha256:f0dc34e2fb8a8fc2a2ee955e74823bd41539b28801ecdd8b3882f47b0d17c8b5"],"state_sha256":"5fa74bdf30a307912611c830abac224a02b967ddda16afd5fe23ad4027f61ea7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ALhlfnuVS7YrXPjtQ+c0fa0YYk2yHvbn0GEI0v2G8GenGQCG0n+t7z9GPB92sX9QpaNEUwLCf5Eu1QJoqEqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:46:49.648401Z","bundle_sha256":"00b3c6d312e4a8f77f39fad5c764237c7aa148a35ae87351039ef615ada92fb8"}}