{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZUDYG4KHGJOSCVXB7QSVD3BHTX","short_pith_number":"pith:ZUDYG4KH","schema_version":"1.0","canonical_sha256":"cd07837147325d2156e1fc2551ec279de8c02a6f6ef9f44783c8ced70fbe8ea3","source":{"kind":"arxiv","id":"2606.04461","version":1},"attestation_state":"computed","paper":{"title":"ChannelTok: Efficient Flexible-Length Vision Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arpit Bansal, Sukriti Paul, Tom Goldstein","submitted_at":"2026-06-03T05:10:51Z","abstract_excerpt":"Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoders. We depart from this complex, spatial-token paradigm and introduce a simple, lightweight, and fast channel-wise flexible-length tokenizer. Our method treats each latent channel as a visual token, enabling a parameter-efficient CNN-Transformer hybrid backbone. Furthermore, employing a stochastic tail-dropping paradigm during training naturally forces channels to organize by semantic importance. This allows for flexible compression at inference"},"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":"2606.04461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T05:10:51Z","cross_cats_sorted":[],"title_canon_sha256":"6652ed5ffa41c98de476b1eedd191b39957845b6c189d991da175540cb1e7e40","abstract_canon_sha256":"25d2faecc280054ca333321c41cd177287ac79e968999a3c45e12d19691e526b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:09.085337Z","signature_b64":"bUO8d2ouuVKYkl81OwPfpQdhl1jtB8rNYD0O8jo/S3xnpREtoybg2PYFZubVlH1sMUxJ2MhI3nVuJySNSmQrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd07837147325d2156e1fc2551ec279de8c02a6f6ef9f44783c8ced70fbe8ea3","last_reissued_at":"2026-06-04T01:09:09.084720Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:09.084720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChannelTok: Efficient Flexible-Length Vision Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arpit Bansal, Sukriti Paul, Tom Goldstein","submitted_at":"2026-06-03T05:10:51Z","abstract_excerpt":"Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoders. We depart from this complex, spatial-token paradigm and introduce a simple, lightweight, and fast channel-wise flexible-length tokenizer. Our method treats each latent channel as a visual token, enabling a parameter-efficient CNN-Transformer hybrid backbone. Furthermore, employing a stochastic tail-dropping paradigm during training naturally forces channels to organize by semantic importance. This allows for flexible compression at inference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04461","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/2606.04461/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":"2606.04461","created_at":"2026-06-04T01:09:09.084813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04461v1","created_at":"2026-06-04T01:09:09.084813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04461","created_at":"2026-06-04T01:09:09.084813+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUDYG4KHGJOS","created_at":"2026-06-04T01:09:09.084813+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUDYG4KHGJOSCVXB","created_at":"2026-06-04T01:09:09.084813+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUDYG4KH","created_at":"2026-06-04T01:09:09.084813+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/ZUDYG4KHGJOSCVXB7QSVD3BHTX","json":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX.json","graph_json":"https://pith.science/api/pith-number/ZUDYG4KHGJOSCVXB7QSVD3BHTX/graph.json","events_json":"https://pith.science/api/pith-number/ZUDYG4KHGJOSCVXB7QSVD3BHTX/events.json","paper":"https://pith.science/paper/ZUDYG4KH"},"agent_actions":{"view_html":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX","download_json":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX.json","view_paper":"https://pith.science/paper/ZUDYG4KH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04461&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUDYG4KHGJOSCVXB7QSVD3BHTX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUDYG4KHGJOSCVXB7QSVD3BHTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX/action/storage_attestation","attest_author":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX/action/author_attestation","sign_citation":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX/action/citation_signature","submit_replication":"https://pith.science/pith/ZUDYG4KHGJOSCVXB7QSVD3BHTX/action/replication_record"}},"created_at":"2026-06-04T01:09:09.084813+00:00","updated_at":"2026-06-04T01:09:09.084813+00:00"}