{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BWZWF43X5VV7XA4B5SEII6MCGN","short_pith_number":"pith:BWZWF43X","canonical_record":{"source":{"id":"2410.10798","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:57:18Z","cross_cats_sorted":[],"title_canon_sha256":"4560753e7f8a450823bc332329ca50d3d44d4cace1a381afb69f73419f3c8dba","abstract_canon_sha256":"8abf5547e5a642a4f60207c6022493ef5979ed543d8b42654d8b51fece3daf6a"},"schema_version":"1.0"},"canonical_sha256":"0db362f377ed6bfb8381ec888479823355b80086eb53b6af55e1072ff275b122","source":{"kind":"arxiv","id":"2410.10798","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10798","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10798v3","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10798","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"BWZWF43X5VV7","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"BWZWF43X5VV7XA4B","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"BWZWF43X","created_at":"2026-07-05T11:15:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BWZWF43X5VV7XA4B5SEII6MCGN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10798","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:57:18Z","cross_cats_sorted":[],"title_canon_sha256":"4560753e7f8a450823bc332329ca50d3d44d4cace1a381afb69f73419f3c8dba","abstract_canon_sha256":"8abf5547e5a642a4f60207c6022493ef5979ed543d8b42654d8b51fece3daf6a"},"schema_version":"1.0"},"canonical_sha256":"0db362f377ed6bfb8381ec888479823355b80086eb53b6af55e1072ff275b122","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:39.747590Z","signature_b64":"f/F1kqyAc2JWKcBSKykomj7eVFE64nn5PkndsbzuN/0adbQfmEeCCu48pc44Q90tX8ZzewaWHHENhsJnH/GsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0db362f377ed6bfb8381ec888479823355b80086eb53b6af55e1072ff275b122","last_reissued_at":"2026-07-05T11:15:39.747113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:39.747113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10798","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":"2026-07-05T11:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UblfZPWFnHyXHe5z99YUoaaIIyuHjRl4MwzB/7ZqQ3I1dQnExbfDkW+9S8JKvY1DsHo+TuuTxo98w0bCjtykAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:49:14.549119Z"},"content_sha256":"6ca2a573c5512ae54710de55ac9b8c60c144bb22da320725f1333cb8c041a237","schema_version":"1.0","event_id":"sha256:6ca2a573c5512ae54710de55ac9b8c60c144bb22da320725f1333cb8c041a237"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BWZWF43X5VV7XA4B5SEII6MCGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Yin, Fengyun Rao, Jian Yang, Wei Zhai, Yang Cao, Yizhou Zhou, Zheng-Jun Zha","submitted_at":"2024-10-14T17:57:18Z","abstract_excerpt":"Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of image information during understanding task, due to either image discretization or diffusion denoising steps. To address this issue, we propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way. Differing f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10798","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/2410.10798/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":"2026-07-05T11:15:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TWV78aoGQW2OO5m4wgD7g+7oeJAGrP4oOEmpnDeMJTI+lclk3SR10jTrbtU7PhpzcNF+Eor5E0pPZbNjoXgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T17:49:14.549635Z"},"content_sha256":"801cf1e9f38ae8a04452d39d85c62a597f782d55ce9d9ec1ac7eb0b7a4a6fbe3","schema_version":"1.0","event_id":"sha256:801cf1e9f38ae8a04452d39d85c62a597f782d55ce9d9ec1ac7eb0b7a4a6fbe3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BWZWF43X5VV7XA4B5SEII6MCGN/bundle.json","state_url":"https://pith.science/pith/BWZWF43X5VV7XA4B5SEII6MCGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BWZWF43X5VV7XA4B5SEII6MCGN/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":"2026-08-12T17:49:14Z","links":{"resolver":"https://pith.science/pith/BWZWF43X5VV7XA4B5SEII6MCGN","bundle":"https://pith.science/pith/BWZWF43X5VV7XA4B5SEII6MCGN/bundle.json","state":"https://pith.science/pith/BWZWF43X5VV7XA4B5SEII6MCGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BWZWF43X5VV7XA4B5SEII6MCGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BWZWF43X5VV7XA4B5SEII6MCGN","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":"8abf5547e5a642a4f60207c6022493ef5979ed543d8b42654d8b51fece3daf6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:57:18Z","title_canon_sha256":"4560753e7f8a450823bc332329ca50d3d44d4cace1a381afb69f73419f3c8dba"},"schema_version":"1.0","source":{"id":"2410.10798","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10798","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10798v3","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10798","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"BWZWF43X5VV7","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"BWZWF43X5VV7XA4B","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"BWZWF43X","created_at":"2026-07-05T11:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:801cf1e9f38ae8a04452d39d85c62a597f782d55ce9d9ec1ac7eb0b7a4a6fbe3","target":"graph","created_at":"2026-07-05T11:15:39Z","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/2410.10798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of image information during understanding task, due to either image discretization or diffusion denoising steps. To address this issue, we propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way. Differing f","authors_text":"Dacheng Yin, Fengyun Rao, Jian Yang, Wei Zhai, Yang Cao, Yizhou Zhou, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:57:18Z","title":"MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10798","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":"sha256:6ca2a573c5512ae54710de55ac9b8c60c144bb22da320725f1333cb8c041a237","target":"record","created_at":"2026-07-05T11:15:39Z","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":"8abf5547e5a642a4f60207c6022493ef5979ed543d8b42654d8b51fece3daf6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:57:18Z","title_canon_sha256":"4560753e7f8a450823bc332329ca50d3d44d4cace1a381afb69f73419f3c8dba"},"schema_version":"1.0","source":{"id":"2410.10798","kind":"arxiv","version":3}},"canonical_sha256":"0db362f377ed6bfb8381ec888479823355b80086eb53b6af55e1072ff275b122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0db362f377ed6bfb8381ec888479823355b80086eb53b6af55e1072ff275b122","first_computed_at":"2026-07-05T11:15:39.747113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:39.747113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f/F1kqyAc2JWKcBSKykomj7eVFE64nn5PkndsbzuN/0adbQfmEeCCu48pc44Q90tX8ZzewaWHHENhsJnH/GsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:39.747590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10798","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ca2a573c5512ae54710de55ac9b8c60c144bb22da320725f1333cb8c041a237","sha256:801cf1e9f38ae8a04452d39d85c62a597f782d55ce9d9ec1ac7eb0b7a4a6fbe3"],"state_sha256":"27060b44039509d1de32c0a24464087b4d88ce47fb0fcce9abf60f4c3930ec78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"on2xFZiW4Q8XTNR4+bBEEw10h+zvsqL9kBa1xvr5q7kycvpYyH7YACxG7AHu8L457HR7Pj/Voanlth0IhjdnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T17:49:14.555398Z","bundle_sha256":"f93538ec7db3be8c7f4b804dec576e5e0ab909e870c630ff91e87ef05e8c3403"}}