{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:POWNTUBRHIUTSIXCQD6F6OHB3O","short_pith_number":"pith:POWNTUBR","canonical_record":{"source":{"id":"2505.07538","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-12T13:19:08Z","cross_cats_sorted":[],"title_canon_sha256":"ec2e265ccb40d51de5d40bc00667a11a73ae045da827dbc456476fc7e04635d7","abstract_canon_sha256":"da7320e71ad5bcca60ce428cd93870a4a7b020442717f054ff7210c2016e47b3"},"schema_version":"1.0"},"canonical_sha256":"7bacd9d0313a293922e280fc5f38e1db949fd891a918fb7ff24fe3ef02dac93b","source":{"kind":"arxiv","id":"2505.07538","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07538","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07538v3","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07538","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"POWNTUBRHIUT","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"POWNTUBRHIUTSIXC","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"POWNTUBR","created_at":"2026-07-05T11:10:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:POWNTUBRHIUTSIXCQD6F6OHB3O","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07538","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-12T13:19:08Z","cross_cats_sorted":[],"title_canon_sha256":"ec2e265ccb40d51de5d40bc00667a11a73ae045da827dbc456476fc7e04635d7","abstract_canon_sha256":"da7320e71ad5bcca60ce428cd93870a4a7b020442717f054ff7210c2016e47b3"},"schema_version":"1.0"},"canonical_sha256":"7bacd9d0313a293922e280fc5f38e1db949fd891a918fb7ff24fe3ef02dac93b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:07.800109Z","signature_b64":"5k8PiQD1CxJwFhFBC1z+Knr5iY8teHKyYrv+1DiKzR8mRmUskDAVe+Igwsao6CGJ682us1SNrdx2kjPSVkH7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bacd9d0313a293922e280fc5f38e1db949fd891a918fb7ff24fe3ef02dac93b","last_reissued_at":"2026-07-05T11:10:07.799610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:07.799610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07538","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ECBpsdy8eJ7iST2M9jeA3IzwZP3CJ5LIb2GPeivygMjcnke7lD45uZpPQ3p+9ifgEeqAGEPvAaJ+qliNNjkeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:49:39.679272Z"},"content_sha256":"a6972fcef825585ce0de43e21daa4489d6f6defbeb37029d60ea5f69105ddef6","schema_version":"1.0","event_id":"sha256:a6972fcef825585ce0de43e21daa4489d6f6defbeb37029d60ea5f69105ddef6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:POWNTUBRHIUTSIXCQD6F6OHB3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Wang, Fengda Zhang, Hanwang Zhang, Jiachun Pan, Junzhe Zhang, Kaihang Pan, Kennard Yanting Chan, Li'an Bi, Liyu Jia, Mingze Zhou, Saining Zhang, Shuo Chen, Wang Lin, Weijia Wu, Wei Zhao, Wentao Hu, Xue Song, Zhongqi Yue","submitted_at":"2025-05-12T13:19:08Z","abstract_excerpt":"We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the causal structure of language -- into visual tokens by using the reverse diffusion process of image generation. The AR property makes Selftok fundamentally distinct from traditional spatial tokens in the following two key ways: - Selftok offers an elegant and minimalist approach to unify diffusion and AR for vision-language models (VLMs): By representing ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07538","kind":"arxiv","version":3},"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/2505.07538/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eWCRuW4Z4MWt2SJkgYkIlLmr04IZ3g6porYjAPvIzCYDfo7Yxg/Up+DehfXFpCYlWXI9NvqVr6ltbswTkxOHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:49:39.679664Z"},"content_sha256":"e662d51913d8cd46fba89d1204374aac0a6754f0c88c4d34faa6953f69a0c00d","schema_version":"1.0","event_id":"sha256:e662d51913d8cd46fba89d1204374aac0a6754f0c88c4d34faa6953f69a0c00d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POWNTUBRHIUTSIXCQD6F6OHB3O/bundle.json","state_url":"https://pith.science/pith/POWNTUBRHIUTSIXCQD6F6OHB3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POWNTUBRHIUTSIXCQD6F6OHB3O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T20:49:39Z","links":{"resolver":"https://pith.science/pith/POWNTUBRHIUTSIXCQD6F6OHB3O","bundle":"https://pith.science/pith/POWNTUBRHIUTSIXCQD6F6OHB3O/bundle.json","state":"https://pith.science/pith/POWNTUBRHIUTSIXCQD6F6OHB3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POWNTUBRHIUTSIXCQD6F6OHB3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:POWNTUBRHIUTSIXCQD6F6OHB3O","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":"da7320e71ad5bcca60ce428cd93870a4a7b020442717f054ff7210c2016e47b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-12T13:19:08Z","title_canon_sha256":"ec2e265ccb40d51de5d40bc00667a11a73ae045da827dbc456476fc7e04635d7"},"schema_version":"1.0","source":{"id":"2505.07538","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07538","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07538v3","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07538","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"POWNTUBRHIUT","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"POWNTUBRHIUTSIXC","created_at":"2026-07-05T11:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"POWNTUBR","created_at":"2026-07-05T11:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:e662d51913d8cd46fba89d1204374aac0a6754f0c88c4d34faa6953f69a0c00d","target":"graph","created_at":"2026-07-05T11:10:07Z","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/2505.07538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We completely discard the conventional spatial prior in image representation and introduce a novel discrete visual tokenizer: Self-consistency Tokenizer (Selftok). At its design core, we compose an autoregressive (AR) prior -- mirroring the causal structure of language -- into visual tokens by using the reverse diffusion process of image generation. The AR property makes Selftok fundamentally distinct from traditional spatial tokens in the following two key ways: - Selftok offers an elegant and minimalist approach to unify diffusion and AR for vision-language models (VLMs): By representing ima","authors_text":"Bohan Wang, Fengda Zhang, Hanwang Zhang, Jiachun Pan, Junzhe Zhang, Kaihang Pan, Kennard Yanting Chan, Li'an Bi, Liyu Jia, Mingze Zhou, Saining Zhang, Shuo Chen, Wang Lin, Weijia Wu, Wei Zhao, Wentao Hu, Xue Song, Zhongqi Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-12T13:19:08Z","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07538","kind":"arxiv","version":3},"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:a6972fcef825585ce0de43e21daa4489d6f6defbeb37029d60ea5f69105ddef6","target":"record","created_at":"2026-07-05T11:10:07Z","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":"da7320e71ad5bcca60ce428cd93870a4a7b020442717f054ff7210c2016e47b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-12T13:19:08Z","title_canon_sha256":"ec2e265ccb40d51de5d40bc00667a11a73ae045da827dbc456476fc7e04635d7"},"schema_version":"1.0","source":{"id":"2505.07538","kind":"arxiv","version":3}},"canonical_sha256":"7bacd9d0313a293922e280fc5f38e1db949fd891a918fb7ff24fe3ef02dac93b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bacd9d0313a293922e280fc5f38e1db949fd891a918fb7ff24fe3ef02dac93b","first_computed_at":"2026-07-05T11:10:07.799610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:07.799610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5k8PiQD1CxJwFhFBC1z+Knr5iY8teHKyYrv+1DiKzR8mRmUskDAVe+Igwsao6CGJ682us1SNrdx2kjPSVkH7Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:07.800109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07538","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6972fcef825585ce0de43e21daa4489d6f6defbeb37029d60ea5f69105ddef6","sha256:e662d51913d8cd46fba89d1204374aac0a6754f0c88c4d34faa6953f69a0c00d"],"state_sha256":"a9a18375fbe8463e9c41701ed5883eac5eca87968fd5629b2c3bb7cffbe346d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HYG3gmwy0xC7BOtd/XGWEv+PjDP+Qwu1qy5TGD6vSVwkQAjiVU7suDgH9es58IgW1UVqrJn+lAGXPgDhz8OgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:49:39.681716Z","bundle_sha256":"70970029ad8567ec8b739daa644677cdfdc457ef3f1df6f92c00b946198c412d"}}