{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TIA5MDFCZRRITUTNJI2TSWPTWT","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":"ea4679ac53102653496e1c916aa2119e2d09fd51dc34348077c65bc66ef05b0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:43:21Z","title_canon_sha256":"0b3d777218c440784c6ddeb4f7dbc756265311711708bb07e160423a16ee8cb0"},"schema_version":"1.0","source":{"id":"2412.14145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14145","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14145v1","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14145","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"TIA5MDFCZRRI","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_16","alias_value":"TIA5MDFCZRRITUTN","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_8","alias_value":"TIA5MDFC","created_at":"2026-07-05T09:51:14Z"}],"graph_snapshots":[{"event_id":"sha256:61e4d2fca91b32f3adf502f1f3b595d426d43770a884eca1e7ccfb7474af38ab","target":"graph","created_at":"2026-07-05T09:51:14Z","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/2412.14145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The visual understanding are often approached from 3 granular levels: image, patch and pixel. Visual Tokenization, trained by self-supervised reconstructive learning, compresses visual data by codebook in patch-level with marginal information loss, but the visual tokens does not have semantic meaning. Open Vocabulary semantic segmentation benefits from the evolving Vision-Language models (VLMs) with strong image zero-shot capability, but transferring image-level to pixel-level understanding remains an imminent challenge. In this paper, we treat segmentation as tokenizing pixels and study a uni","authors_text":"Jianyu Zhang, Li Zhang, Shijian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:43:21Z","title":"Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14145","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":"sha256:8f045521cc73d364e60c470a45d71a54be4955a94d18b7cc9754faf77b28231e","target":"record","created_at":"2026-07-05T09:51:14Z","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":"ea4679ac53102653496e1c916aa2119e2d09fd51dc34348077c65bc66ef05b0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T18:43:21Z","title_canon_sha256":"0b3d777218c440784c6ddeb4f7dbc756265311711708bb07e160423a16ee8cb0"},"schema_version":"1.0","source":{"id":"2412.14145","kind":"arxiv","version":1}},"canonical_sha256":"9a01d60ca2cc6289d26d4a353959f3b4cd098baf6e7b687598233cb23c036543","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a01d60ca2cc6289d26d4a353959f3b4cd098baf6e7b687598233cb23c036543","first_computed_at":"2026-07-05T09:51:14.305011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:14.305011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6AHCLGgAD5n+IuH/LxGx0ZmTIYtuNLnrP3DvevxrLYBYH49SArWtHdJo6QncT5p4ScKAwZDKlhokoZmFPz/qAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:14.305560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f045521cc73d364e60c470a45d71a54be4955a94d18b7cc9754faf77b28231e","sha256:61e4d2fca91b32f3adf502f1f3b595d426d43770a884eca1e7ccfb7474af38ab"],"state_sha256":"44ab24175b3636dfc5c3284312111102ed2f45c0b83af04abe5c5b13a093ca59"}