{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:35J6JPDLD7FBQKWE37SVZ47N73","short_pith_number":"pith:35J6JPDL","schema_version":"1.0","canonical_sha256":"df53e4bc6b1fca182ac4dfe55cf3edfec9ab28f35ea4bbbb2cc246fe6a94c4d7","source":{"kind":"arxiv","id":"2412.07612","version":3},"attestation_state":"computed","paper":{"title":"ViewDelta: Scaling Scene Change Detection through Text-Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joshua Gao, Subin Varghese, Vedhus Hoskere","submitted_at":"2024-12-10T15:51:17Z","abstract_excerpt":"We introduce a generalized framework for Scene Change Detection (SCD) that addresses the core ambiguity of distinguishing \"relevant\" from \"nuisance\" changes, enabling effective joint training of a single model across diverse domains and applications. Existing methods struggle to generalize due to differences in dataset labeling, where changes such as vegetation growth or lane marking alterations may be labeled as relevant in one dataset and irrelevant in another. To resolve this ambiguity, we propose ViewDelta, a text conditioned change detection framework that uses natural language prompts to"},"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":"2412.07612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T15:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"a85e1892edde1a877c2d420b6af0a149e780acbf48849ea20b2db76830cba871","abstract_canon_sha256":"fb7cb3e104edc890caaa23ecc2be2fa1143df08dce130dfb96d98261c948c747"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:58.170863Z","signature_b64":"3rcvoKYlQiQ4mH4kyxwcYsUFZBnodAlv7o3a5hsOKWOLXV6LZbE3RJx7qgv11wBWFYO972aXJe3DYuJc7i7xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df53e4bc6b1fca182ac4dfe55cf3edfec9ab28f35ea4bbbb2cc246fe6a94c4d7","last_reissued_at":"2026-07-05T11:52:58.170361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:58.170361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViewDelta: Scaling Scene Change Detection through Text-Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joshua Gao, Subin Varghese, Vedhus Hoskere","submitted_at":"2024-12-10T15:51:17Z","abstract_excerpt":"We introduce a generalized framework for Scene Change Detection (SCD) that addresses the core ambiguity of distinguishing \"relevant\" from \"nuisance\" changes, enabling effective joint training of a single model across diverse domains and applications. Existing methods struggle to generalize due to differences in dataset labeling, where changes such as vegetation growth or lane marking alterations may be labeled as relevant in one dataset and irrelevant in another. To resolve this ambiguity, we propose ViewDelta, a text conditioned change detection framework that uses natural language prompts to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07612","kind":"arxiv","version":3},"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/2412.07612/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":"2412.07612","created_at":"2026-07-05T11:52:58.170421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07612v3","created_at":"2026-07-05T11:52:58.170421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07612","created_at":"2026-07-05T11:52:58.170421+00:00"},{"alias_kind":"pith_short_12","alias_value":"35J6JPDLD7FB","created_at":"2026-07-05T11:52:58.170421+00:00"},{"alias_kind":"pith_short_16","alias_value":"35J6JPDLD7FBQKWE","created_at":"2026-07-05T11:52:58.170421+00:00"},{"alias_kind":"pith_short_8","alias_value":"35J6JPDL","created_at":"2026-07-05T11:52:58.170421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11402","citing_title":"SCD4VPR: Multi-modal Scene Change Detection for Long-term Visual Place Recognition Database Update","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73","json":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73.json","graph_json":"https://pith.science/api/pith-number/35J6JPDLD7FBQKWE37SVZ47N73/graph.json","events_json":"https://pith.science/api/pith-number/35J6JPDLD7FBQKWE37SVZ47N73/events.json","paper":"https://pith.science/paper/35J6JPDL"},"agent_actions":{"view_html":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73","download_json":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73.json","view_paper":"https://pith.science/paper/35J6JPDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07612&json=true","fetch_graph":"https://pith.science/api/pith-number/35J6JPDLD7FBQKWE37SVZ47N73/graph.json","fetch_events":"https://pith.science/api/pith-number/35J6JPDLD7FBQKWE37SVZ47N73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73/action/storage_attestation","attest_author":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73/action/author_attestation","sign_citation":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73/action/citation_signature","submit_replication":"https://pith.science/pith/35J6JPDLD7FBQKWE37SVZ47N73/action/replication_record"}},"created_at":"2026-07-05T11:52:58.170421+00:00","updated_at":"2026-07-05T11:52:58.170421+00:00"}