{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IQRDQSO2LWTEQUQ2P67KP2BBJM","short_pith_number":"pith:IQRDQSO2","schema_version":"1.0","canonical_sha256":"44223849da5da648521a7fbea7e8214b28c1f396ec87a2122c1d15a878c9cfd7","source":{"kind":"arxiv","id":"2501.07256","version":1},"attestation_state":"computed","paper":{"title":"EdgeTAM: On-Device Track Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bilge Soran, Bo Dai, Chen Change Loy, Chenchen Zhu, Chong Zhou, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Saksham Suri, Vikas Chandra, Yunyang Xiong","submitted_at":"2025-01-13T12:11:07Z","abstract_excerpt":"On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to video inputs through a memory bank mechanism and obtains a remarkable performance compared with previous methods, making it a foundation model for video segmentation task. In this paper, we aim at making SAM 2 much more efficient so that it even runs on mobile devices while maintaining a comparable performance. Despite several works optimizing SAM for better efficiency, we find they are not sufficient for SAM 2 because they all focus on compressing the image encoder, while our benchmark shows that the ne"},"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":"2501.07256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T12:11:07Z","cross_cats_sorted":[],"title_canon_sha256":"80217afe75639a82dfe287e658afe8b3a7df49fd55d99801d72d3e4213a0e508","abstract_canon_sha256":"5a4ffb7b92b49b396f82839ed97d7a2ce3c238a8c96bb613ccc14e726d45ed14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:17.991424Z","signature_b64":"zb03PSXB4PDLpqGumwVsCR74GTsfXyeeQakYtklH3hl7AG2CewUjULTiF/MYU1PujZm2eHK7X9I/EJJvq1I7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44223849da5da648521a7fbea7e8214b28c1f396ec87a2122c1d15a878c9cfd7","last_reissued_at":"2026-07-05T10:00:17.990980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:17.990980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdgeTAM: On-Device Track Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bilge Soran, Bo Dai, Chen Change Loy, Chenchen Zhu, Chong Zhou, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Saksham Suri, Vikas Chandra, Yunyang Xiong","submitted_at":"2025-01-13T12:11:07Z","abstract_excerpt":"On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to video inputs through a memory bank mechanism and obtains a remarkable performance compared with previous methods, making it a foundation model for video segmentation task. In this paper, we aim at making SAM 2 much more efficient so that it even runs on mobile devices while maintaining a comparable performance. Despite several works optimizing SAM for better efficiency, we find they are not sufficient for SAM 2 because they all focus on compressing the image encoder, while our benchmark shows that the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07256","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/2501.07256/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.07256","created_at":"2026-07-05T10:00:17.991040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07256v1","created_at":"2026-07-05T10:00:17.991040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07256","created_at":"2026-07-05T10:00:17.991040+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQRDQSO2LWTE","created_at":"2026-07-05T10:00:17.991040+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQRDQSO2LWTEQUQ2","created_at":"2026-07-05T10:00:17.991040+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQRDQSO2","created_at":"2026-07-05T10:00:17.991040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14271","citing_title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM","json":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM.json","graph_json":"https://pith.science/api/pith-number/IQRDQSO2LWTEQUQ2P67KP2BBJM/graph.json","events_json":"https://pith.science/api/pith-number/IQRDQSO2LWTEQUQ2P67KP2BBJM/events.json","paper":"https://pith.science/paper/IQRDQSO2"},"agent_actions":{"view_html":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM","download_json":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM.json","view_paper":"https://pith.science/paper/IQRDQSO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07256&json=true","fetch_graph":"https://pith.science/api/pith-number/IQRDQSO2LWTEQUQ2P67KP2BBJM/graph.json","fetch_events":"https://pith.science/api/pith-number/IQRDQSO2LWTEQUQ2P67KP2BBJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM/action/storage_attestation","attest_author":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM/action/author_attestation","sign_citation":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM/action/citation_signature","submit_replication":"https://pith.science/pith/IQRDQSO2LWTEQUQ2P67KP2BBJM/action/replication_record"}},"created_at":"2026-07-05T10:00:17.991040+00:00","updated_at":"2026-07-05T10:00:17.991040+00:00"}