{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7FPRI5EM2S2KAUA5NIKSTEPK2V","short_pith_number":"pith:7FPRI5EM","canonical_record":{"source":{"id":"2605.14346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T04:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"4afb830fda38fe75a4e703f92785496841b75ebbef869effa29e5d5703c469e7","abstract_canon_sha256":"1d51feb6af4f80b86f7da916ee49def1894888b390c06b8f0d005e9b1e1aca8e"},"schema_version":"1.0"},"canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","source":{"kind":"arxiv","id":"2605.14346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14346","created_at":"2026-05-17T23:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14346v1","created_at":"2026-05-17T23:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14346","created_at":"2026-05-17T23:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"7FPRI5EM2S2K","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7FPRI5EM2S2KAUA5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7FPRI5EM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7FPRI5EM2S2KAUA5NIKSTEPK2V","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T04:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"4afb830fda38fe75a4e703f92785496841b75ebbef869effa29e5d5703c469e7","abstract_canon_sha256":"1d51feb6af4f80b86f7da916ee49def1894888b390c06b8f0d005e9b1e1aca8e"},"schema_version":"1.0"},"canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:08.127176Z","signature_b64":"6RNoNNS3BnHPiXM+M8X6B7BAZUUHXtH3twjjxuE7q8DarQhQYJOl5XG+ve3Qml+CbcrkMCPYADYwPU3VQFZzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","last_reissued_at":"2026-05-17T23:39:08.126535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:08.126535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14346","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":"2026-05-17T23:39:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpRgDSBA4b7BCZ2bgpxYyktTapQ7v8elc+hw3HYSxVvH73uJtrw/Hk41swVJyrmSHzVV6+C/U3S/0rkM5n72Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:54:21.016905Z"},"content_sha256":"f4f0b073eb90dfe56069015114159ee93d544c06add4b336d82f00c58b2c55e9","schema_version":"1.0","event_id":"sha256:f4f0b073eb90dfe56069015114159ee93d544c06add4b336d82f00c58b2c55e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7FPRI5EM2S2KAUA5NIKSTEPK2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Ma, Ping Qian, Weimin Wang, Yuanhang Yao, Zhu Liu","submitted_at":"2026-05-14T04:12:08Z","abstract_excerpt":"Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training... Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a frozen general-purpose VFM can reliably supply semantic priors transferable to infrared small targets via SCAM modulation and bilevel optimization without domain-specific adaptation or overfitting to the training distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hierarchical VFM-driven knowledge distillation method with semantic-conditioned modulation and cluster reweighting stabilizes point-supervised infrared small target detection and improves accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2dfc64c51977f9e2fd4cc20158b156bbb91b576ccde15fc81d3310efdf8b5f09"},"source":{"id":"2605.14346","kind":"arxiv","version":1},"verdict":{"id":"83eec166-015c-4727-bea5-54ce31a9ad45","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:53:14.361858Z","strongest_claim":"We propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training... Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability.","one_line_summary":"A hierarchical VFM-driven knowledge distillation method with semantic-conditioned modulation and cluster reweighting stabilizes point-supervised infrared small target detection and improves accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a frozen general-purpose VFM can reliably supply semantic priors transferable to infrared small targets via SCAM modulation and bilevel optimization without domain-specific adaptation or overfitting to the training distribution.","pith_extraction_headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation."},"references":{"count":23,"sample":[{"doi":"","year":2010,"title":"Anal- ysis of new top-hat transformation and the application for infrared dim small target detection.Pattern Recognition, 43(6):2145–2156,","work_id":"a7776eb3-857e-41eb-a18c-a7e19f693675","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"A local contrast method for small infrared target detection.IEEE Transactions on Geoscience and Remote Sensing, 52(1):574–581,","work_id":"a767532b-4763-40fd-8af9-963fbe5bbc2d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Asymmetric contextual modulation for infrared small target detection","work_id":"ca269583-e519-45a7-97d8-dc1fdfb5c346","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Segment Anything","work_id":"0c3b519e-074e-4112-a638-275301245293","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Dense nested attention network for infrared small target detection.IEEE Transactions on Image Processing, 32:1745–1758,","work_id":"f6ab96a5-2933-40f2-8040-53bf96aae0a9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"275e0220fa717406996fc4c1e2e8c76239f5bcfa3a403bb9bb4214237c669892","internal_anchors":2},"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":"83eec166-015c-4727-bea5-54ce31a9ad45"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afFLM08qFD8AiHMQiyHZfwxBNro/Ybb9Rfariix6c1u7uSOZUBzHyGhZwSVaRepyQ/x535OtX1bsqAQDvM7IBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:54:21.017572Z"},"content_sha256":"d150cd722cf725a73715c17390e4a6df9a36b5b8ce16356b61da93ccff085b76","schema_version":"1.0","event_id":"sha256:d150cd722cf725a73715c17390e4a6df9a36b5b8ce16356b61da93ccff085b76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/bundle.json","state_url":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/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":"2026-05-21T19:54:21Z","links":{"resolver":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V","bundle":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/bundle.json","state":"https://pith.science/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7FPRI5EM2S2KAUA5NIKSTEPK2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7FPRI5EM2S2KAUA5NIKSTEPK2V","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":"1d51feb6af4f80b86f7da916ee49def1894888b390c06b8f0d005e9b1e1aca8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T04:12:08Z","title_canon_sha256":"4afb830fda38fe75a4e703f92785496841b75ebbef869effa29e5d5703c469e7"},"schema_version":"1.0","source":{"id":"2605.14346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14346","created_at":"2026-05-17T23:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14346v1","created_at":"2026-05-17T23:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14346","created_at":"2026-05-17T23:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"7FPRI5EM2S2K","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7FPRI5EM2S2KAUA5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7FPRI5EM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d150cd722cf725a73715c17390e4a6df9a36b5b8ce16356b61da93ccff085b76","target":"graph","created_at":"2026-05-17T23:39:08Z","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":"We propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training... Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a frozen general-purpose VFM can reliably supply semantic priors transferable to infrared small targets via SCAM modulation and bilevel optimization without domain-specific adaptation or overfitting to the training distribution."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A hierarchical VFM-driven knowledge distillation method with semantic-conditioned modulation and cluster reweighting stabilizes point-supervised infrared small target detection and improves accuracy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation."}],"snapshot_sha256":"2dfc64c51977f9e2fd4cc20158b156bbb91b576ccde15fc81d3310efdf8b5f09"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop ","authors_text":"Long Ma, Ping Qian, Weimin Wang, Yuanhang Yao, Zhu Liu","cross_cats":[],"headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T04:12:08Z","title":"Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation"},"references":{"count":23,"internal_anchors":2,"resolved_work":23,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Anal- ysis of new top-hat transformation and the application for infrared dim small target detection.Pattern Recognition, 43(6):2145–2156,","work_id":"a7776eb3-857e-41eb-a18c-a7e19f693675","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A local contrast method for small infrared target detection.IEEE Transactions on Geoscience and Remote Sensing, 52(1):574–581,","work_id":"a767532b-4763-40fd-8af9-963fbe5bbc2d","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Asymmetric contextual modulation for infrared small target detection","work_id":"ca269583-e519-45a7-97d8-dc1fdfb5c346","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Segment Anything","work_id":"0c3b519e-074e-4112-a638-275301245293","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Dense nested attention network for infrared small target detection.IEEE Transactions on Image Processing, 32:1745–1758,","work_id":"f6ab96a5-2933-40f2-8040-53bf96aae0a9","year":2023}],"snapshot_sha256":"275e0220fa717406996fc4c1e2e8c76239f5bcfa3a403bb9bb4214237c669892"},"source":{"id":"2605.14346","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:53:14.361858Z","id":"83eec166-015c-4727-bea5-54ce31a9ad45","model_set":{"reader":"grok-4.3"},"one_line_summary":"A hierarchical VFM-driven knowledge distillation method with semantic-conditioned modulation and cluster reweighting stabilizes point-supervised infrared small target detection and improves accuracy.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A frozen vision foundation model supplies semantic priors to stabilize point-supervised infrared small target detection through hierarchical distillation.","strongest_claim":"We propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training... Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability.","weakest_assumption":"That a frozen general-purpose VFM can reliably supply semantic priors transferable to infrared small targets via SCAM modulation and bilevel optimization without domain-specific adaptation or overfitting to the training distribution."}},"verdict_id":"83eec166-015c-4727-bea5-54ce31a9ad45"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f4f0b073eb90dfe56069015114159ee93d544c06add4b336d82f00c58b2c55e9","target":"record","created_at":"2026-05-17T23:39:08Z","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":"1d51feb6af4f80b86f7da916ee49def1894888b390c06b8f0d005e9b1e1aca8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T04:12:08Z","title_canon_sha256":"4afb830fda38fe75a4e703f92785496841b75ebbef869effa29e5d5703c469e7"},"schema_version":"1.0","source":{"id":"2605.14346","kind":"arxiv","version":1}},"canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f95f14748cd4b4a0501d6a152991ead57215fd15f26aa6709dff94411c0f7970","first_computed_at":"2026-05-17T23:39:08.126535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:08.126535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6RNoNNS3BnHPiXM+M8X6B7BAZUUHXtH3twjjxuE7q8DarQhQYJOl5XG+ve3Qml+CbcrkMCPYADYwPU3VQFZzCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:08.127176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4f0b073eb90dfe56069015114159ee93d544c06add4b336d82f00c58b2c55e9","sha256:d150cd722cf725a73715c17390e4a6df9a36b5b8ce16356b61da93ccff085b76"],"state_sha256":"3b9c4f340947cf30f9e44d44047cdb2eeb4ca94e598f61d11a2ab048187362d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PMQBpW2IUAWOZMohiCGb4Uzw09XHUdgAbiS5dw0d0mBVpFK4puiP2Vm/2BOuE9HnOUoORJp0R82NMePbn5qUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T19:54:21.020207Z","bundle_sha256":"77fc1c2c0c9c677b0e17e28acab1a0da3b2dabb2d309b23097e338363b328ca3"}}