{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ERSLGMLH5F5MKL5CUI4XTEJDDN","short_pith_number":"pith:ERSLGMLH","schema_version":"1.0","canonical_sha256":"2464b33167e97ac52fa2a2397991231b5d27314d86d85b5b31ca0e4692d88d32","source":{"kind":"arxiv","id":"2605.18013","version":1},"attestation_state":"computed","paper":{"title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Shu, Xinghao Chen, Yijing Yang, Zhaoyuan Ding","submitted_at":"2026-05-18T08:05:59Z","abstract_excerpt":"Segment Anything Model 2 (SAM 2) serves as a core foundation model in the field of video segmentation. Building upon the original SAM model, it introduces a memory bank mechanism and demonstrates outstanding performance in tasks such as semi-supervised video object segmentation and tracking anything. However, the complex computational characteristics of SAM 2's multi-stage image encoder and memory module have raised the barrier to the model's deployment in practical applications. To address this issue, we propose TinySAM 2, a lightweight video segmentation model that balances performance and e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.18013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:05:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a90d5e475bee970eedc2895a1d50287abe48b07d625f5c867988e8f2289f2c68","abstract_canon_sha256":"c28ff8a3c2e4bf7eade90f4b6b1d5b505c0468ca2267a128738fc29ac08daf1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:11.297037Z","signature_b64":"X4MXTO9dk0PIrG14hgfbUi6bQ4s1qkJCz0+XtD/VukoZw/mIlQGAYpHiilNXqf1EctMenC1cjOfZgHeq6IpkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2464b33167e97ac52fa2a2397991231b5d27314d86d85b5b31ca0e4692d88d32","last_reissued_at":"2026-05-20T00:05:11.296208Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:11.296208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Shu, Xinghao Chen, Yijing Yang, Zhaoyuan Ding","submitted_at":"2026-05-18T08:05:59Z","abstract_excerpt":"Segment Anything Model 2 (SAM 2) serves as a core foundation model in the field of video segmentation. Building upon the original SAM model, it introduces a memory bank mechanism and demonstrates outstanding performance in tasks such as semi-supervised video object segmentation and tracking anything. However, the complex computational characteristics of SAM 2's multi-stage image encoder and memory module have raised the barrier to the model's deployment in practical applications. To address this issue, we propose TinySAM 2, a lightweight video segmentation model that balances performance and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18013","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/2605.18013/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.527803Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"207dcb28126e668e9324f03cbe293157312f734a59a33eec44c6a4f26de9af3e"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.18013","created_at":"2026-05-20T00:05:11.296347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18013v1","created_at":"2026-05-20T00:05:11.296347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18013","created_at":"2026-05-20T00:05:11.296347+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERSLGMLH5F5M","created_at":"2026-05-20T00:05:11.296347+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERSLGMLH5F5MKL5C","created_at":"2026-05-20T00:05:11.296347+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERSLGMLH","created_at":"2026-05-20T00:05:11.296347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN","json":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN.json","graph_json":"https://pith.science/api/pith-number/ERSLGMLH5F5MKL5CUI4XTEJDDN/graph.json","events_json":"https://pith.science/api/pith-number/ERSLGMLH5F5MKL5CUI4XTEJDDN/events.json","paper":"https://pith.science/paper/ERSLGMLH"},"agent_actions":{"view_html":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN","download_json":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN.json","view_paper":"https://pith.science/paper/ERSLGMLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18013&json=true","fetch_graph":"https://pith.science/api/pith-number/ERSLGMLH5F5MKL5CUI4XTEJDDN/graph.json","fetch_events":"https://pith.science/api/pith-number/ERSLGMLH5F5MKL5CUI4XTEJDDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN/action/storage_attestation","attest_author":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN/action/author_attestation","sign_citation":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN/action/citation_signature","submit_replication":"https://pith.science/pith/ERSLGMLH5F5MKL5CUI4XTEJDDN/action/replication_record"}},"created_at":"2026-05-20T00:05:11.296347+00:00","updated_at":"2026-05-20T00:05:11.296347+00:00"}