{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VVGD3KHWMAF2JSG72HQ7GYVRHS","short_pith_number":"pith:VVGD3KHW","canonical_record":{"source":{"id":"2606.05758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T06:37:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"24ac2ffbcc1964057c60c4fa3bfbdb4b0bd2b7d01662cdcfac5794404c5e31c3","abstract_canon_sha256":"cea2d1c386066e57a0530fbfea620a6a7b3a3a32bc1bbfcd6a18c1a2166e6257"},"schema_version":"1.0"},"canonical_sha256":"ad4c3da8f6600ba4c8dfd1e1f362b13cb32e31e8bb1947adcea949d63148e3c7","source":{"kind":"arxiv","id":"2606.05758","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05758","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05758v1","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05758","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"VVGD3KHWMAF2","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_16","alias_value":"VVGD3KHWMAF2JSG7","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_8","alias_value":"VVGD3KHW","created_at":"2026-06-05T01:15:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VVGD3KHWMAF2JSG72HQ7GYVRHS","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T06:37:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"24ac2ffbcc1964057c60c4fa3bfbdb4b0bd2b7d01662cdcfac5794404c5e31c3","abstract_canon_sha256":"cea2d1c386066e57a0530fbfea620a6a7b3a3a32bc1bbfcd6a18c1a2166e6257"},"schema_version":"1.0"},"canonical_sha256":"ad4c3da8f6600ba4c8dfd1e1f362b13cb32e31e8bb1947adcea949d63148e3c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:02.037585Z","signature_b64":"Cr1ycsEB6M7JsCcaPyMxfXnEs+iq+K3Bxocfd0Bbh/yLikUyPYXHgG0+3agL2BXsJTch1EYzFkbVtoTZXsiLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad4c3da8f6600ba4c8dfd1e1f362b13cb32e31e8bb1947adcea949d63148e3c7","last_reissued_at":"2026-06-05T01:15:02.036891Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:02.036891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05758","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdVoszLGbJWLB1ivWbQ1yqavghg/Yk2EyjQDbwEF+qJONUnQM8IuI3DUeUMB++INJjAZuhdWUEO0y2PRbPCqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:24:09.150648Z"},"content_sha256":"8afeeb64e1114b3253570a0c8a094cd5b10cc9d55189a3c13b984a55f3db8ff4","schema_version":"1.0","event_id":"sha256:8afeeb64e1114b3253570a0c8a094cd5b10cc9d55189a3c13b984a55f3db8ff4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VVGD3KHWMAF2JSG72HQ7GYVRHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jinhong Lin, Kwan Man Cheng, Lin Zhang, Shayok Bagchi, Yin Li, Zhuoming Liu","submitted_at":"2026-06-04T06:37:10Z","abstract_excerpt":"Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens. While text-based output interfaces enable scalable pretraining and strong zero-shot generalization across diverse tasks, they are poorly suited for problems that require precise continuous outputs, such as localizing temporal boundaries of events or generating robotic control actions. To address this challenge, we propose DRIFT, a general framework for adapting pretrained VLMs to continuous decoding tasks. DRIFT combines a base predictor, which provides a coarse estimate of the target output, with a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05758","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/2606.05758/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":"2026-06-05T01:15:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wBauT6KL2/Z8cNWG+9//onJkL54LqmnDqZdgDdaXiTa0KeX71/moU7iXo9c+XLU9nwfZQHwci2wMs9N6bS2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:24:09.151020Z"},"content_sha256":"30f1607a32d730044323eb7228516a06a89ddcaf97195eea439c2d5561e36602","schema_version":"1.0","event_id":"sha256:30f1607a32d730044323eb7228516a06a89ddcaf97195eea439c2d5561e36602"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS/bundle.json","state_url":"https://pith.science/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS/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":"2026-07-02T21:24:09Z","links":{"resolver":"https://pith.science/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS","bundle":"https://pith.science/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS/bundle.json","state":"https://pith.science/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVGD3KHWMAF2JSG72HQ7GYVRHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VVGD3KHWMAF2JSG72HQ7GYVRHS","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":"cea2d1c386066e57a0530fbfea620a6a7b3a3a32bc1bbfcd6a18c1a2166e6257","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T06:37:10Z","title_canon_sha256":"24ac2ffbcc1964057c60c4fa3bfbdb4b0bd2b7d01662cdcfac5794404c5e31c3"},"schema_version":"1.0","source":{"id":"2606.05758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05758","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05758v1","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05758","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"VVGD3KHWMAF2","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_16","alias_value":"VVGD3KHWMAF2JSG7","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_8","alias_value":"VVGD3KHW","created_at":"2026-06-05T01:15:02Z"}],"graph_snapshots":[{"event_id":"sha256:30f1607a32d730044323eb7228516a06a89ddcaf97195eea439c2d5561e36602","target":"graph","created_at":"2026-06-05T01:15:02Z","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/2606.05758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens. While text-based output interfaces enable scalable pretraining and strong zero-shot generalization across diverse tasks, they are poorly suited for problems that require precise continuous outputs, such as localizing temporal boundaries of events or generating robotic control actions. To address this challenge, we propose DRIFT, a general framework for adapting pretrained VLMs to continuous decoding tasks. DRIFT combines a base predictor, which provides a coarse estimate of the target output, with a ","authors_text":"Jinhong Lin, Kwan Man Cheng, Lin Zhang, Shayok Bagchi, Yin Li, Zhuoming Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T06:37:10Z","title":"DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05758","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":"sha256:8afeeb64e1114b3253570a0c8a094cd5b10cc9d55189a3c13b984a55f3db8ff4","target":"record","created_at":"2026-06-05T01:15:02Z","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":"cea2d1c386066e57a0530fbfea620a6a7b3a3a32bc1bbfcd6a18c1a2166e6257","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T06:37:10Z","title_canon_sha256":"24ac2ffbcc1964057c60c4fa3bfbdb4b0bd2b7d01662cdcfac5794404c5e31c3"},"schema_version":"1.0","source":{"id":"2606.05758","kind":"arxiv","version":1}},"canonical_sha256":"ad4c3da8f6600ba4c8dfd1e1f362b13cb32e31e8bb1947adcea949d63148e3c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad4c3da8f6600ba4c8dfd1e1f362b13cb32e31e8bb1947adcea949d63148e3c7","first_computed_at":"2026-06-05T01:15:02.036891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:02.036891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cr1ycsEB6M7JsCcaPyMxfXnEs+iq+K3Bxocfd0Bbh/yLikUyPYXHgG0+3agL2BXsJTch1EYzFkbVtoTZXsiLBw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:02.037585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05758","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8afeeb64e1114b3253570a0c8a094cd5b10cc9d55189a3c13b984a55f3db8ff4","sha256:30f1607a32d730044323eb7228516a06a89ddcaf97195eea439c2d5561e36602"],"state_sha256":"0370af03e2cc71e10c3e109b124e0a899afaac0680a15fd59d8fa876bcb3a52f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7psdVRbkhjUP5YtlRqacup4M5Q7NOXnKQOlNy0zhQyiokmvYcd/sC2QrNDaECL4u5R30uWkMlVZxzuX+bNoiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T21:24:09.152984Z","bundle_sha256":"0e5630f493f1f331e19aaa76c9179da06c0ad7a51ab8646f8b0de4d659c6c71e"}}