{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5F7NWAAXPLVHZEXZ54IRMT5N7Q","short_pith_number":"pith:5F7NWAAX","canonical_record":{"source":{"id":"2509.17901","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-22T15:28:54Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"342efc416f5c6445f8ad5c87639451d61e726d55f4b33a7ec9547d4202f560cc","abstract_canon_sha256":"1bb23ecf533a11fe267d3891738d2de9a04081141195a156b884c3e496f4e96a"},"schema_version":"1.0"},"canonical_sha256":"e97edb00177aea7c92f9ef11164fadfc13f1dd29372bf57206ab68bf43113212","source":{"kind":"arxiv","id":"2509.17901","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.17901","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"2509.17901v4","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.17901","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"5F7NWAAXPLVH","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"pith_short_16","alias_value":"5F7NWAAXPLVHZEXZ","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"pith_short_8","alias_value":"5F7NWAAX","created_at":"2026-06-23T02:13:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5F7NWAAXPLVHZEXZ54IRMT5N7Q","target":"record","payload":{"canonical_record":{"source":{"id":"2509.17901","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-22T15:28:54Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"342efc416f5c6445f8ad5c87639451d61e726d55f4b33a7ec9547d4202f560cc","abstract_canon_sha256":"1bb23ecf533a11fe267d3891738d2de9a04081141195a156b884c3e496f4e96a"},"schema_version":"1.0"},"canonical_sha256":"e97edb00177aea7c92f9ef11164fadfc13f1dd29372bf57206ab68bf43113212","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:16.874148Z","signature_b64":"2iU121u2ZBVJ5Z4QSjLpBDE71A/2fQE68QgwPWK2nj662RPJ/h7vr1G3AxcQLTpFAB25VojiW0vNtP5VZeWIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e97edb00177aea7c92f9ef11164fadfc13f1dd29372bf57206ab68bf43113212","last_reissued_at":"2026-06-23T02:13:16.873757Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:16.873757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.17901","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XH8dK2eURH+Ncv6rtBaoxzaGPS/1Zj2pJYficC250PPnMEo6XuUc5wcP2VNGNWqS3vQQg8F89mwNHkT3kboJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:00:45.942200Z"},"content_sha256":"666ad71fcada0552f342bf5469e86ea0eec4dc721bebff91307f53aab8f71cb9","schema_version":"1.0","event_id":"sha256:666ad71fcada0552f342bf5469e86ea0eec4dc721bebff91307f53aab8f71cb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5F7NWAAXPLVHZEXZ54IRMT5N7Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Geewook Kim, Minjoon Seo","submitted_at":"2025-09-22T15:28:54Z","abstract_excerpt":"Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers about 76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25-fold token reduction (25 Hz to 1 Hz). Across 10 benchmarks, with and without filtering,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.17901","kind":"arxiv","version":4},"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/2509.17901/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":"2026-06-23T02:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmwTGSRXKJIH7Gz7Xgr8OWIUiEr2mh0i09MJa+zMCu5U0D32pOKTf0vcwCguC1yNmI/Ox3VYiwy2dThSAqZ+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:00:45.942588Z"},"content_sha256":"45eeb9b14db176cd55038474eb17662174dfccf3104e9ac69869869546df220d","schema_version":"1.0","event_id":"sha256:45eeb9b14db176cd55038474eb17662174dfccf3104e9ac69869869546df220d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q/bundle.json","state_url":"https://pith.science/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q/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":"2026-06-30T16:00:45Z","links":{"resolver":"https://pith.science/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q","bundle":"https://pith.science/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q/bundle.json","state":"https://pith.science/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5F7NWAAXPLVHZEXZ54IRMT5N7Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5F7NWAAXPLVHZEXZ54IRMT5N7Q","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":"1bb23ecf533a11fe267d3891738d2de9a04081141195a156b884c3e496f4e96a","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-22T15:28:54Z","title_canon_sha256":"342efc416f5c6445f8ad5c87639451d61e726d55f4b33a7ec9547d4202f560cc"},"schema_version":"1.0","source":{"id":"2509.17901","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.17901","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"2509.17901v4","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.17901","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"5F7NWAAXPLVH","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"pith_short_16","alias_value":"5F7NWAAXPLVHZEXZ","created_at":"2026-06-23T02:13:16Z"},{"alias_kind":"pith_short_8","alias_value":"5F7NWAAX","created_at":"2026-06-23T02:13:16Z"}],"graph_snapshots":[{"event_id":"sha256:45eeb9b14db176cd55038474eb17662174dfccf3104e9ac69869869546df220d","target":"graph","created_at":"2026-06-23T02:13:16Z","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/2509.17901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers about 76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25-fold token reduction (25 Hz to 1 Hz). Across 10 benchmarks, with and without filtering,","authors_text":"Geewook Kim, Minjoon Seo","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-22T15:28:54Z","title":"Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.17901","kind":"arxiv","version":4},"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":"sha256:666ad71fcada0552f342bf5469e86ea0eec4dc721bebff91307f53aab8f71cb9","target":"record","created_at":"2026-06-23T02:13:16Z","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":"1bb23ecf533a11fe267d3891738d2de9a04081141195a156b884c3e496f4e96a","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-22T15:28:54Z","title_canon_sha256":"342efc416f5c6445f8ad5c87639451d61e726d55f4b33a7ec9547d4202f560cc"},"schema_version":"1.0","source":{"id":"2509.17901","kind":"arxiv","version":4}},"canonical_sha256":"e97edb00177aea7c92f9ef11164fadfc13f1dd29372bf57206ab68bf43113212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e97edb00177aea7c92f9ef11164fadfc13f1dd29372bf57206ab68bf43113212","first_computed_at":"2026-06-23T02:13:16.873757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:16.873757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2iU121u2ZBVJ5Z4QSjLpBDE71A/2fQE68QgwPWK2nj662RPJ/h7vr1G3AxcQLTpFAB25VojiW0vNtP5VZeWIAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:16.874148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.17901","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:666ad71fcada0552f342bf5469e86ea0eec4dc721bebff91307f53aab8f71cb9","sha256:45eeb9b14db176cd55038474eb17662174dfccf3104e9ac69869869546df220d"],"state_sha256":"e536efc5de03c3d3d0a098e245dd605eacf2c8cea7cef1816fc8365f7285e7cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6N+x+h7x7zzzUXj1aPG0dQ+KXh0XY9rpKNIrS9uUHyn4xVFS48oI7iE7SSi1ud13IOyrbKcb06bJBIupDsqcDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T16:00:45.944571Z","bundle_sha256":"6dd1e9840f0f7525cdbb72ceace3d4b099f2dde226fe421e79669ee163ef08e2"}}