{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NO6CY7DAGK6FHI6SZCLGCUJYDR","short_pith_number":"pith:NO6CY7DA","canonical_record":{"source":{"id":"2306.14289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-25T16:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"4becd44a08c66d2aaa9186af9b0864a26f2d60ff538c3b3d3185e17a643bc367","abstract_canon_sha256":"262fac928c7e47438491724ca07d6e870797dc053df61f2173e6c21a926a9a38"},"schema_version":"1.0"},"canonical_sha256":"6bbc2c7c6032bc53a3d2c8966151381c64e83197a00b969fc960c1b941ae98f6","source":{"kind":"arxiv","id":"2306.14289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14289","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14289v2","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14289","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"NO6CY7DAGK6F","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NO6CY7DAGK6FHI6S","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NO6CY7DA","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NO6CY7DAGK6FHI6SZCLGCUJYDR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.14289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-25T16:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"4becd44a08c66d2aaa9186af9b0864a26f2d60ff538c3b3d3185e17a643bc367","abstract_canon_sha256":"262fac928c7e47438491724ca07d6e870797dc053df61f2173e6c21a926a9a38"},"schema_version":"1.0"},"canonical_sha256":"6bbc2c7c6032bc53a3d2c8966151381c64e83197a00b969fc960c1b941ae98f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:12.783281Z","signature_b64":"9aFLeEfXQN8Rv+UdiyeLnuAHLBYJiqD9++DWxIAZrFMb9Jk88y3M4OL1B0AQ5zDNrt4gZH7siuypqrs+BSwDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bbc2c7c6032bc53a3d2c8966151381c64e83197a00b969fc960c1b941ae98f6","last_reissued_at":"2026-05-17T23:38:12.782631Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:12.782631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.14289","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":"2026-05-17T23:38:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/R+AYtTB9gnHZ0WWZe/juDdR1Jus8mVhqBou0JxcgOUYIAR+seLX5/2FZ4Ler0asRQABn5u5gZA54SZssppDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:57:10.707050Z"},"content_sha256":"14f483f3c87173f2c0d0670f2adc844abb8eb32ea6fd55397e152a3e45e3a567","schema_version":"1.0","event_id":"sha256:14f483f3c87173f2c0d0670f2adc844abb8eb32ea6fd55397e152a3e45e3a567"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NO6CY7DAGK6FHI6SZCLGCUJYDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Distilling SAM's heavy encoder into a lightweight one creates MobileSAM, over 60 times smaller with matching zero-shot segmentation performance.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Choong Seon Hong, Dongshen Han, Jung Uk Kim, Seungkyu Lee, Sung-Ho Bae, Yu Qiao","submitted_at":"2023-06-25T16:37:25Z","abstract_excerpt":"Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one. A naive way to train such a new SAM as in the original SAM paper leads to unsatisfactory performance, especially when limited training sources are available. We find "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that a lightweight encoder distilled only from the frozen original encoder will remain compatible with the original mask decoder across diverse downstream tasks without further joint fine-tuning","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Distilling SAM's heavy encoder into a lightweight one creates MobileSAM, over 60 times smaller with matching zero-shot segmentation performance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"56fb1bfec08cd2eae39b54bb9581db78395a38832c2c1f23c2ada5d67f8d3d86"},"source":{"id":"2306.14289","kind":"arxiv","version":2},"verdict":{"id":"9db7228b-9ee9-4bbc-84c1-da0bad73d9af","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T22:37:57.264741Z","strongest_claim":"the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM","one_line_summary":"MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that a lightweight encoder distilled only from the frozen original encoder will remain compatible with the original mask decoder across diverse downstream tasks without further joint fine-tuning","pith_extraction_headline":"Distilling SAM's heavy encoder into a lightweight one creates MobileSAM, over 60 times smaller with matching zero-shot segmentation performance."},"references":{"count":18,"sample":[{"doi":"","year":null,"title":"One small step for generative ai, one giant leap for agi: A complete survey on chatgpt in aigc era","work_id":"e0645322-bb71-4701-b9ff-134537e95fe8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"On the Opportunities and Risks of Foundation Models","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","ref_index":2,"cited_arxiv_id":"2108.07258","is_internal_anchor":true},{"doi":"","year":null,"title":"Mp-fedcl: Multi-prototype federated contrastive learning for edge intelligence","work_id":"c0a2ea68-d6a5-40cb-97a0-b9abfac75009","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Fast segment anything","work_id":"feed3d9f-cc9f-42db-90e6-e9ff051cef57","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Segment anything in medical images","work_id":"b64c0fe5-9896-4720-94a0-9f05513ee885","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"2a62ff75b5da33cefb09495749782b1555582fb10f7511aa6c0deb8f0e9a575e","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8025b99c4461f43a4c3d613f9306938736a764a247dc06bde4265860b4459920"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"9db7228b-9ee9-4bbc-84c1-da0bad73d9af"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCEgJEKv8OejrJ8a3z9WMLp66HRr4+DMikQ0Z4694NYxUF1oLg1vZgPpgNGvB4cdF3AgGQkX7uIo4g42bTdRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:57:10.708010Z"},"content_sha256":"90eb64205b7cac50cd4464b1da3ae6688452fdebaed88ebce6f79b7d801614ad","schema_version":"1.0","event_id":"sha256:90eb64205b7cac50cd4464b1da3ae6688452fdebaed88ebce6f79b7d801614ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR/bundle.json","state_url":"https://pith.science/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR/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":"2026-06-06T18:57:10Z","links":{"resolver":"https://pith.science/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR","bundle":"https://pith.science/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR/bundle.json","state":"https://pith.science/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NO6CY7DAGK6FHI6SZCLGCUJYDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NO6CY7DAGK6FHI6SZCLGCUJYDR","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":"262fac928c7e47438491724ca07d6e870797dc053df61f2173e6c21a926a9a38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-25T16:37:25Z","title_canon_sha256":"4becd44a08c66d2aaa9186af9b0864a26f2d60ff538c3b3d3185e17a643bc367"},"schema_version":"1.0","source":{"id":"2306.14289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14289","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14289v2","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14289","created_at":"2026-05-17T23:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"NO6CY7DAGK6F","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NO6CY7DAGK6FHI6S","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NO6CY7DA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:90eb64205b7cac50cd4464b1da3ae6688452fdebaed88ebce6f79b7d801614ad","target":"graph","created_at":"2026-05-17T23:38:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"that a lightweight encoder distilled only from the frozen original encoder will remain compatible with the original mask decoder across diverse downstream tasks without further joint fine-tuning"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Distilling SAM's heavy encoder into a lightweight one creates MobileSAM, over 60 times smaller with matching zero-shot segmentation performance."}],"snapshot_sha256":"56fb1bfec08cd2eae39b54bb9581db78395a38832c2c1f23c2ada5d67f8d3d86"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8025b99c4461f43a4c3d613f9306938736a764a247dc06bde4265860b4459920"},"paper":{"abstract_excerpt":"Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one. A naive way to train such a new SAM as in the original SAM paper leads to unsatisfactory performance, especially when limited training sources are available. We find ","authors_text":"Chaoning Zhang, Choong Seon Hong, Dongshen Han, Jung Uk Kim, Seungkyu Lee, Sung-Ho Bae, Yu Qiao","cross_cats":[],"headline":"Distilling SAM's heavy encoder into a lightweight one creates MobileSAM, over 60 times smaller with matching zero-shot segmentation performance.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-25T16:37:25Z","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications"},"references":{"count":18,"internal_anchors":4,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"One small step for generative ai, one giant leap for agi: A complete survey on chatgpt in aigc era","work_id":"e0645322-bb71-4701-b9ff-134537e95fe8","year":null},{"cited_arxiv_id":"2108.07258","doi":"","is_internal_anchor":true,"ref_index":2,"title":"On the Opportunities and Risks of Foundation Models","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Mp-fedcl: Multi-prototype federated contrastive learning for edge intelligence","work_id":"c0a2ea68-d6a5-40cb-97a0-b9abfac75009","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Fast segment anything","work_id":"feed3d9f-cc9f-42db-90e6-e9ff051cef57","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Segment anything in medical images","work_id":"b64c0fe5-9896-4720-94a0-9f05513ee885","year":null}],"snapshot_sha256":"2a62ff75b5da33cefb09495749782b1555582fb10f7511aa6c0deb8f0e9a575e"},"source":{"id":"2306.14289","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T22:37:57.264741Z","id":"9db7228b-9ee9-4bbc-84c1-da0bad73d9af","model_set":{"reader":"grok-4.3"},"one_line_summary":"MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Distilling SAM's heavy encoder into a lightweight one creates MobileSAM, over 60 times smaller with matching zero-shot segmentation performance.","strongest_claim":"the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM","weakest_assumption":"that a lightweight encoder distilled only from the frozen original encoder will remain compatible with the original mask decoder across diverse downstream tasks without further joint fine-tuning"}},"verdict_id":"9db7228b-9ee9-4bbc-84c1-da0bad73d9af"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:14f483f3c87173f2c0d0670f2adc844abb8eb32ea6fd55397e152a3e45e3a567","target":"record","created_at":"2026-05-17T23:38:12Z","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":"262fac928c7e47438491724ca07d6e870797dc053df61f2173e6c21a926a9a38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-25T16:37:25Z","title_canon_sha256":"4becd44a08c66d2aaa9186af9b0864a26f2d60ff538c3b3d3185e17a643bc367"},"schema_version":"1.0","source":{"id":"2306.14289","kind":"arxiv","version":2}},"canonical_sha256":"6bbc2c7c6032bc53a3d2c8966151381c64e83197a00b969fc960c1b941ae98f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bbc2c7c6032bc53a3d2c8966151381c64e83197a00b969fc960c1b941ae98f6","first_computed_at":"2026-05-17T23:38:12.782631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:12.782631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9aFLeEfXQN8Rv+UdiyeLnuAHLBYJiqD9++DWxIAZrFMb9Jk88y3M4OL1B0AQ5zDNrt4gZH7siuypqrs+BSwDBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:12.783281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14f483f3c87173f2c0d0670f2adc844abb8eb32ea6fd55397e152a3e45e3a567","sha256:90eb64205b7cac50cd4464b1da3ae6688452fdebaed88ebce6f79b7d801614ad"],"state_sha256":"c22a14bcd9512469f39976a9959140fc13dcc555aa8cae267804f8b6dcbbd668"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M1RYiKa1Iy1MPQ+nMAV3XI5KDznhR6UZT1JI7VqyFcyw6UqsBu79lrUKf+Ds10dOT1CC1EMYy0d2dMYdPW3KBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:57:10.712411Z","bundle_sha256":"2cb6b0a25421250a40537bae89cec8a316bdb33daa7d66eeba89052fdd311e1a"}}