{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:555AWMECNXE6L3WOIEUBPRXCVT","short_pith_number":"pith:555AWMEC","schema_version":"1.0","canonical_sha256":"ef7a0b30826dc9e5eece412817c6e2acd4494350cc702bd9a117e82b85ccf6a8","source":{"kind":"arxiv","id":"2607.04044","version":1},"attestation_state":"computed","paper":{"title":"SiamJEPA: On the Role of Siamese Student Encoders in JEPA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Makoto Yamada","submitted_at":"2026-07-04T22:09:41Z","abstract_excerpt":"Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning. Unlike masked autoencoders that reconstruct pixels, JEPA models learn representations by predicting latent embeddings of masked regions. Existing JEPA-based methods, such as I-JEPA and V-JEPA, typically employ a single encoder in the student network. In contrast, using Siamese encoders for student network is more naturally aligned with brain-inspired representation learning f"},"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":"2607.04044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-04T22:09:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"60eb126e898e6c51cdc904df80f5306c8b773d8de801d42f8ba8b733076b1235","abstract_canon_sha256":"749ea5bbf4c282b6cd184a7caf0d4653a8864294d5e21bb655bd5393446e395b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:54.787735Z","signature_b64":"XKEJUf8G8Z+J32RiGagR1C6A397/yeoE/IxfkTTSB2y7l3H5sDxx8ZyXK8UuPCmGtSUGsv+Hb1TMKRKlsndjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7a0b30826dc9e5eece412817c6e2acd4494350cc702bd9a117e82b85ccf6a8","last_reissued_at":"2026-07-07T02:18:54.787032Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:54.787032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SiamJEPA: On the Role of Siamese Student Encoders in JEPA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Makoto Yamada","submitted_at":"2026-07-04T22:09:41Z","abstract_excerpt":"Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning. Unlike masked autoencoders that reconstruct pixels, JEPA models learn representations by predicting latent embeddings of masked regions. Existing JEPA-based methods, such as I-JEPA and V-JEPA, typically employ a single encoder in the student network. In contrast, using Siamese encoders for student network is more naturally aligned with brain-inspired representation learning f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04044","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/2607.04044/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":"2607.04044","created_at":"2026-07-07T02:18:54.787143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04044v1","created_at":"2026-07-07T02:18:54.787143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04044","created_at":"2026-07-07T02:18:54.787143+00:00"},{"alias_kind":"pith_short_12","alias_value":"555AWMECNXE6","created_at":"2026-07-07T02:18:54.787143+00:00"},{"alias_kind":"pith_short_16","alias_value":"555AWMECNXE6L3WO","created_at":"2026-07-07T02:18:54.787143+00:00"},{"alias_kind":"pith_short_8","alias_value":"555AWMEC","created_at":"2026-07-07T02:18:54.787143+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/555AWMECNXE6L3WOIEUBPRXCVT","json":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT.json","graph_json":"https://pith.science/api/pith-number/555AWMECNXE6L3WOIEUBPRXCVT/graph.json","events_json":"https://pith.science/api/pith-number/555AWMECNXE6L3WOIEUBPRXCVT/events.json","paper":"https://pith.science/paper/555AWMEC"},"agent_actions":{"view_html":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT","download_json":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT.json","view_paper":"https://pith.science/paper/555AWMEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04044&json=true","fetch_graph":"https://pith.science/api/pith-number/555AWMECNXE6L3WOIEUBPRXCVT/graph.json","fetch_events":"https://pith.science/api/pith-number/555AWMECNXE6L3WOIEUBPRXCVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT/action/storage_attestation","attest_author":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT/action/author_attestation","sign_citation":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT/action/citation_signature","submit_replication":"https://pith.science/pith/555AWMECNXE6L3WOIEUBPRXCVT/action/replication_record"}},"created_at":"2026-07-07T02:18:54.787143+00:00","updated_at":"2026-07-07T02:18:54.787143+00:00"}