{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:26METU7HL52OAKQ6OXOCSBMVGR","short_pith_number":"pith:26METU7H","canonical_record":{"source":{"id":"2509.15874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-19T11:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"14fdd6fc97a17e19054c9d4bdf7cbccd1cbaa3e8758503ccd5e34a05bd12bd71","abstract_canon_sha256":"87a64a91b479e16eaa3ebfff5fc20c9e3ff876b505661199e096404f68d1db91"},"schema_version":"1.0"},"canonical_sha256":"d79849d3e75f74e02a1e75dc290595346c5f25412dab311ef03f237464a9b691","source":{"kind":"arxiv","id":"2509.15874","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.15874","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.15874v1","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15874","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"26METU7HL52O","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"pith_short_16","alias_value":"26METU7HL52OAKQ6","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"pith_short_8","alias_value":"26METU7H","created_at":"2026-07-02T01:17:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:26METU7HL52OAKQ6OXOCSBMVGR","target":"record","payload":{"canonical_record":{"source":{"id":"2509.15874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-19T11:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"14fdd6fc97a17e19054c9d4bdf7cbccd1cbaa3e8758503ccd5e34a05bd12bd71","abstract_canon_sha256":"87a64a91b479e16eaa3ebfff5fc20c9e3ff876b505661199e096404f68d1db91"},"schema_version":"1.0"},"canonical_sha256":"d79849d3e75f74e02a1e75dc290595346c5f25412dab311ef03f237464a9b691","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:24.417613Z","signature_b64":"q8RjSJVp2Cz/pRK/jdn3rO+7MZkN6qBf+hB3UZNa2HHDrQZIx2k/WBZpLDuoTUexXNpieGFVq9ntbnYjk0n5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79849d3e75f74e02a1e75dc290595346c5f25412dab311ef03f237464a9b691","last_reissued_at":"2026-07-02T01:17:24.417185Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:24.417185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.15874","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":"2026-07-02T01:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCCjbiGaNfpFuuxTul0BVGGCIISw4hEDVgduHKFoSrQ3sVuzprELAE8cpEgG52PV7mUXhagivtoMM/ICD9nACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T02:04:11.895305Z"},"content_sha256":"4ebe209f98f30bc5b8ac6be7dc2d0f001657b1b25186b7931979a3caf99d112b","schema_version":"1.0","event_id":"sha256:4ebe209f98f30bc5b8ac6be7dc2d0f001657b1b25186b7931979a3caf99d112b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:26METU7HL52OAKQ6OXOCSBMVGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ENSAM: an efficient foundation model for interactive segmentation of 3D medical images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agnar Martin Bj{\\o}rnstad, Arian Ranjbar, Elias Stenhede","submitted_at":"2025-09-19T11:20:22Z","abstract_excerpt":"We present ENSAM (Equivariant, Normalized, Segment Anything Model), a lightweight and promptable model for universal 3D medical image segmentation. ENSAM combines a SegResNet-based encoder with a prompt encoder and mask decoder in a U-Net-style architecture, using latent cross-attention, relative positional encoding, normalized attention, and the Muon optimizer for training. ENSAM is designed to achieve good performance under limited data and computational budgets, and is trained from scratch on under 5,000 volumes from multiple modalities (CT, MRI, PET, ultrasound, microscopy) on a single 32 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15874","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/2509.15874/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":"2026-07-02T01:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhYR6pHkEgrHbvCGxYJ/qh0LsjcA2MNHIkdhqrG5ilUN+4Laeylp5H9kf3V19GSHZMJVeL6XQT+CjtcE1ZrJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T02:04:11.895711Z"},"content_sha256":"9cd5691887b966427097bb4839eed1138ca353c73ca5959504754a053fcf47ac","schema_version":"1.0","event_id":"sha256:9cd5691887b966427097bb4839eed1138ca353c73ca5959504754a053fcf47ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26METU7HL52OAKQ6OXOCSBMVGR/bundle.json","state_url":"https://pith.science/pith/26METU7HL52OAKQ6OXOCSBMVGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26METU7HL52OAKQ6OXOCSBMVGR/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":"2026-07-04T02:04:11Z","links":{"resolver":"https://pith.science/pith/26METU7HL52OAKQ6OXOCSBMVGR","bundle":"https://pith.science/pith/26METU7HL52OAKQ6OXOCSBMVGR/bundle.json","state":"https://pith.science/pith/26METU7HL52OAKQ6OXOCSBMVGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26METU7HL52OAKQ6OXOCSBMVGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:26METU7HL52OAKQ6OXOCSBMVGR","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":"87a64a91b479e16eaa3ebfff5fc20c9e3ff876b505661199e096404f68d1db91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-19T11:20:22Z","title_canon_sha256":"14fdd6fc97a17e19054c9d4bdf7cbccd1cbaa3e8758503ccd5e34a05bd12bd71"},"schema_version":"1.0","source":{"id":"2509.15874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.15874","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.15874v1","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15874","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"26METU7HL52O","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"pith_short_16","alias_value":"26METU7HL52OAKQ6","created_at":"2026-07-02T01:17:24Z"},{"alias_kind":"pith_short_8","alias_value":"26METU7H","created_at":"2026-07-02T01:17:24Z"}],"graph_snapshots":[{"event_id":"sha256:9cd5691887b966427097bb4839eed1138ca353c73ca5959504754a053fcf47ac","target":"graph","created_at":"2026-07-02T01:17:24Z","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/2509.15874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ENSAM (Equivariant, Normalized, Segment Anything Model), a lightweight and promptable model for universal 3D medical image segmentation. ENSAM combines a SegResNet-based encoder with a prompt encoder and mask decoder in a U-Net-style architecture, using latent cross-attention, relative positional encoding, normalized attention, and the Muon optimizer for training. ENSAM is designed to achieve good performance under limited data and computational budgets, and is trained from scratch on under 5,000 volumes from multiple modalities (CT, MRI, PET, ultrasound, microscopy) on a single 32 ","authors_text":"Agnar Martin Bj{\\o}rnstad, Arian Ranjbar, Elias Stenhede","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-19T11:20:22Z","title":"ENSAM: an efficient foundation model for interactive segmentation of 3D medical images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15874","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":"sha256:4ebe209f98f30bc5b8ac6be7dc2d0f001657b1b25186b7931979a3caf99d112b","target":"record","created_at":"2026-07-02T01:17:24Z","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":"87a64a91b479e16eaa3ebfff5fc20c9e3ff876b505661199e096404f68d1db91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-19T11:20:22Z","title_canon_sha256":"14fdd6fc97a17e19054c9d4bdf7cbccd1cbaa3e8758503ccd5e34a05bd12bd71"},"schema_version":"1.0","source":{"id":"2509.15874","kind":"arxiv","version":1}},"canonical_sha256":"d79849d3e75f74e02a1e75dc290595346c5f25412dab311ef03f237464a9b691","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d79849d3e75f74e02a1e75dc290595346c5f25412dab311ef03f237464a9b691","first_computed_at":"2026-07-02T01:17:24.417185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:24.417185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q8RjSJVp2Cz/pRK/jdn3rO+7MZkN6qBf+hB3UZNa2HHDrQZIx2k/WBZpLDuoTUexXNpieGFVq9ntbnYjk0n5DQ==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:24.417613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.15874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ebe209f98f30bc5b8ac6be7dc2d0f001657b1b25186b7931979a3caf99d112b","sha256:9cd5691887b966427097bb4839eed1138ca353c73ca5959504754a053fcf47ac"],"state_sha256":"458bbbd899a33eb2bc8de9f3dd67f18c745d22ace000aa09e47b1c16617e2e5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+6ziHKW48nklM8r5Us9Y88D5DjigafdiqPDw7IZYCTq0B1WjQhj6ROZtJMNY9RYzupMPSECDF1q+Ifl2G0WsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T02:04:11.897900Z","bundle_sha256":"5a12959337e9b6c5b5822df2fbfcd3bce75a979b2670d22af994093e533778fd"}}