{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L7RR5VLGSUXSDIO3VFHKCOKKJO","short_pith_number":"pith:L7RR5VLG","schema_version":"1.0","canonical_sha256":"5fe31ed566952f21a1dba94ea1394a4bb111b11868dbb2ca8d2445470ca19615","source":{"kind":"arxiv","id":"2506.17837","version":1},"attestation_state":"computed","paper":{"title":"Time-Contrastive Pretraining for In-Context Image and Video Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhilash Hareendranathan, Assefa Wahd, Jacob Jaremko","submitted_at":"2025-06-21T22:26:20Z","abstract_excerpt":"In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a time-contrastive self-supervised objective that pretrains a prompt retriever for visual ICL, and formulate ICL as a video object segmentation (VOS) task. Temporal addresses key limitations of grid-based methods that restrict the number and resolution of context images. By reframing ICL as a VOS problem, our approach supports a variable number of context imag"},"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":"2506.17837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-21T22:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"63c60ed71f0d68d47862b0d605d4db7ee154d6204e1eb5eb4116d5fee3696ac4","abstract_canon_sha256":"ed2638c545f6a85876bd1b2fbb24689d94f9bd454d67bd1c107adda331d8fe65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:24.075908Z","signature_b64":"pbbkhhgKQClXQI2ezwgOlbhn35b4bdDH8jAXTUpdcTA0nGFYMDh0HStgeIaI7wk0tRQqJXGKKPtK7nOhyS2jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe31ed566952f21a1dba94ea1394a4bb111b11868dbb2ca8d2445470ca19615","last_reissued_at":"2026-07-05T11:25:24.075473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:24.075473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Contrastive Pretraining for In-Context Image and Video Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhilash Hareendranathan, Assefa Wahd, Jacob Jaremko","submitted_at":"2025-06-21T22:26:20Z","abstract_excerpt":"In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a time-contrastive self-supervised objective that pretrains a prompt retriever for visual ICL, and formulate ICL as a video object segmentation (VOS) task. Temporal addresses key limitations of grid-based methods that restrict the number and resolution of context images. By reframing ICL as a VOS problem, our approach supports a variable number of context imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17837","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/2506.17837/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":"2506.17837","created_at":"2026-07-05T11:25:24.075529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17837v1","created_at":"2026-07-05T11:25:24.075529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17837","created_at":"2026-07-05T11:25:24.075529+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7RR5VLGSUXS","created_at":"2026-07-05T11:25:24.075529+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7RR5VLGSUXSDIO3","created_at":"2026-07-05T11:25:24.075529+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7RR5VLG","created_at":"2026-07-05T11:25:24.075529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO","json":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO.json","graph_json":"https://pith.science/api/pith-number/L7RR5VLGSUXSDIO3VFHKCOKKJO/graph.json","events_json":"https://pith.science/api/pith-number/L7RR5VLGSUXSDIO3VFHKCOKKJO/events.json","paper":"https://pith.science/paper/L7RR5VLG"},"agent_actions":{"view_html":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO","download_json":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO.json","view_paper":"https://pith.science/paper/L7RR5VLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17837&json=true","fetch_graph":"https://pith.science/api/pith-number/L7RR5VLGSUXSDIO3VFHKCOKKJO/graph.json","fetch_events":"https://pith.science/api/pith-number/L7RR5VLGSUXSDIO3VFHKCOKKJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO/action/storage_attestation","attest_author":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO/action/author_attestation","sign_citation":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO/action/citation_signature","submit_replication":"https://pith.science/pith/L7RR5VLGSUXSDIO3VFHKCOKKJO/action/replication_record"}},"created_at":"2026-07-05T11:25:24.075529+00:00","updated_at":"2026-07-05T11:25:24.075529+00:00"}