{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PDEZO6ZI5M5RRNJXR7XU24TF2","short_pith_number":"pith:3PDEZO6Z","schema_version":"1.0","canonical_sha256":"dbc64cbbd94759d8c5a9bc7f7a6b932e8ab9076c5b7dd952a43a3b280fa2177c","source":{"kind":"arxiv","id":"2411.10411","version":2},"attestation_state":"computed","paper":{"title":"Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Markus Karmann, Onay Urfalioglu","submitted_at":"2024-11-15T18:29:59Z","abstract_excerpt":"Recent progress in interactive point prompt based Image Segmentation allows to significantly reduce the manual effort to obtain high quality semantic labels. State-of-the-art unsupervised methods use self-supervised pre-trained models to obtain pseudo-labels which are used in training a prompt-based segmentation model. In this paper, we propose a novel unsupervised and training-free approach based solely on the self-attention of Stable Diffusion. We interpret the self-attention tensor as a Markov transition operator, which enables us to iteratively construct a Markov chain. Pixel-wise counting"},"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":"2411.10411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T18:29:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"facc13d45146cd145271b753600d9c84dfbe52587c312f5eccfabf7c8eba09d9","abstract_canon_sha256":"c25dc3679252d06aa983eaa8e1950fcf7a85f7b67ec57a2dfeebad832691ca3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:15.297514Z","signature_b64":"PcJM5kIfkt4Gok27DVDF3NqHd6+wgo8IGDbn2J4I65T5Un2mEXlMrTnBgxaarbJizclFnkpAeKky587aF/5JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc64cbbd94759d8c5a9bc7f7a6b932e8ab9076c5b7dd952a43a3b280fa2177c","last_reissued_at":"2026-07-05T10:36:15.296863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:15.296863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Markus Karmann, Onay Urfalioglu","submitted_at":"2024-11-15T18:29:59Z","abstract_excerpt":"Recent progress in interactive point prompt based Image Segmentation allows to significantly reduce the manual effort to obtain high quality semantic labels. State-of-the-art unsupervised methods use self-supervised pre-trained models to obtain pseudo-labels which are used in training a prompt-based segmentation model. In this paper, we propose a novel unsupervised and training-free approach based solely on the self-attention of Stable Diffusion. We interpret the self-attention tensor as a Markov transition operator, which enables us to iteratively construct a Markov chain. Pixel-wise counting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10411","kind":"arxiv","version":2},"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/2411.10411/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":"2411.10411","created_at":"2026-07-05T10:36:15.296929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10411v2","created_at":"2026-07-05T10:36:15.296929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10411","created_at":"2026-07-05T10:36:15.296929+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PDEZO6ZI5M5","created_at":"2026-07-05T10:36:15.296929+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PDEZO6ZI5M5RRNJ","created_at":"2026-07-05T10:36:15.296929+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PDEZO6Z","created_at":"2026-07-05T10:36:15.296929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.15263","citing_title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2","json":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2.json","graph_json":"https://pith.science/api/pith-number/3PDEZO6ZI5M5RRNJXR7XU24TF2/graph.json","events_json":"https://pith.science/api/pith-number/3PDEZO6ZI5M5RRNJXR7XU24TF2/events.json","paper":"https://pith.science/paper/3PDEZO6Z"},"agent_actions":{"view_html":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2","download_json":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2.json","view_paper":"https://pith.science/paper/3PDEZO6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10411&json=true","fetch_graph":"https://pith.science/api/pith-number/3PDEZO6ZI5M5RRNJXR7XU24TF2/graph.json","fetch_events":"https://pith.science/api/pith-number/3PDEZO6ZI5M5RRNJXR7XU24TF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2/action/storage_attestation","attest_author":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2/action/author_attestation","sign_citation":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2/action/citation_signature","submit_replication":"https://pith.science/pith/3PDEZO6ZI5M5RRNJXR7XU24TF2/action/replication_record"}},"created_at":"2026-07-05T10:36:15.296929+00:00","updated_at":"2026-07-05T10:36:15.296929+00:00"}