{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DE3PD5LEEHVTDXEICQQUHPGYYZ","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":"2e245db531915e07c562dc047bade07833782d6c3b9ce6d9be9920b283117d63","cross_cats_sorted":["q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:04:14Z","title_canon_sha256":"cc6b7c18440de7033537436dcd2da75205bd2ca5c9af5af475ecb4d4149ffa11"},"schema_version":"1.0","source":{"id":"2505.14204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14204","created_at":"2026-07-05T11:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14204v1","created_at":"2026-07-05T11:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14204","created_at":"2026-07-05T11:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"DE3PD5LEEHVT","created_at":"2026-07-05T11:05:57Z"},{"alias_kind":"pith_short_16","alias_value":"DE3PD5LEEHVTDXEI","created_at":"2026-07-05T11:05:57Z"},{"alias_kind":"pith_short_8","alias_value":"DE3PD5LE","created_at":"2026-07-05T11:05:57Z"}],"graph_snapshots":[{"event_id":"sha256:e6cfa14f30a05bb2f89c138594c7f671eb660293cad6726fa003557895e7bdb2","target":"graph","created_at":"2026-07-05T11:05:57Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.14204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Perceptual-Initialization (PI), a paradigm shift in visual representation learning that incorporates human perceptual structure during the initialization phase rather than as a downstream fine-tuning step. By integrating human-derived triplet embeddings from the NIGHTS dataset to initialize a CLIP vision encoder, followed by self-supervised learning on YFCC15M, our approach demonstrates significant zero-shot performance improvements, without any task-specific fine-tuning, across 29 zero shot classification and 2 retrieval benchmarks. On ImageNet-1K, zero-shot gains emerge after ap","authors_text":"David A. Tovar, Do Hun Kim, Mark Wallace, Runchen Wang, Stephen Chong Zhao, Xuhui Zhan, Yang Hu","cross_cats":["q-bio.NC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:04:14Z","title":"Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14204","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50dd4d1fc968e81028915901c79de4263936995fc86cf3461d86e033c4d21a6e","target":"record","created_at":"2026-07-05T11:05:57Z","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":"2e245db531915e07c562dc047bade07833782d6c3b9ce6d9be9920b283117d63","cross_cats_sorted":["q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T11:04:14Z","title_canon_sha256":"cc6b7c18440de7033537436dcd2da75205bd2ca5c9af5af475ecb4d4149ffa11"},"schema_version":"1.0","source":{"id":"2505.14204","kind":"arxiv","version":1}},"canonical_sha256":"1936f1f56421eb31dc88142143bcd8c67224ba97b95ca7ca85518d8d133b6907","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1936f1f56421eb31dc88142143bcd8c67224ba97b95ca7ca85518d8d133b6907","first_computed_at":"2026-07-05T11:05:57.790394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:57.790394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ETY5slJG1cmPQoB4SQzrDdL1szVwVBQCoj28118c4wZGBQvzrB8/TDUXE15L5aGhY8keHsSlpcr0CS/bPBUuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:57.790868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50dd4d1fc968e81028915901c79de4263936995fc86cf3461d86e033c4d21a6e","sha256:e6cfa14f30a05bb2f89c138594c7f671eb660293cad6726fa003557895e7bdb2"],"state_sha256":"0164541a54ebbe5f875d147966be6800a7331a0c2d7b21ff742aae6e5a71e0d0"}